Tags¶

Following is a list of relevant tags:

ALU¶

• CPU Summary

APFS¶

• 파일 시스템 (File System)

ASIC¶

• Integrated Circuit

AUC¶

• Performance Measures for Classifiers

Active Pull-Up¶

• Gate Outputs
• Totem-pole Output

Address¶

• MMU
• memory 기초

Address Binding¶

• MMU

Address Bus¶

• memory 기초

Apple2¶

• History

AutoConnection¶

• Signals and Slots 예제 (Connection Type별)

BASIC¶

• History

BPTT¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

Bahdanau¶

• Attention Score (or Alignment)

Base¶

• Numeral System

Binary¶

• Numeral System

Bit¶

• Bit
• Information

Bitwise¶

• IO Ports

Boolean¶

• Gate에 대해서

Boolean Algebra¶

• Boolean Algebra

Bouncing¶

• Push Btns

Brightness Control¶

• Duty Cycle

CAS¶

• memory 기초

CMOS¶

• Transistor

CPU¶

• CPU Summary

CRT¶

• Library, Shared Library, Dynamic Linking
• Potability and POSIX

CUDA¶

• Parallel Computing

Channel¶

• IO Ports

Classification¶

• Perceptron Loss, Weight Update, SGD, and SVM

Cluster¶

• Parallel Computing

Combinatorial¶

• Gate에 대해서

Common Cathode¶

• FND

Computer¶

• OS

Computer Architecture¶

• Interrupt and Polling

Context¶

• Interrupt and Polling

Control Unit¶

• CPU Summary

Coprocessor¶

• CPU Summary

Core¶

• CPU Summary

Core Memory¶

• RAM

Counter¶

• Counter

D Flip-Flop¶

• Counter

D Latch¶

• Latch

DASD¶

• Block Device

DDR¶

• RAM

DNS¶

• Internet and Related Protocols

DRAM¶

• RAM

Data Bus¶

• memory 기초

De Morgan's Law¶

• Boolean Algebra

Decimal¶

• Numeral System

Declarative¶

• Declarative Programming Language vs. Imperative Programming Language

Decoder¶

• memory 기초

Deep Learning¶

• Recurrent Neural Network

Demand Paging¶

• Virtual Memory

Desktop¶

• 컴퓨터 분류.

Dialog¶

• PySide6 Dialog 기본 코드
• QFileDialog로 file과 directory 선택하기
• QInputDialog

Dialog Box¶

• PySide6 Dialog 기본 코드

Differential Signaling¶

• Noise와 싸우기

Digit¶

• Bit

Diode¶

• Vacuum Tubes

DirectConnection¶

• Signals and Slots 예제 (Connection Type별)

Duty Cycle¶

• Duty Cycle

EDA¶

• Integrated Circuit

EDSAC¶

• History

EDVAC¶

• History

ELF¶

• Library, Shared Library, Dynamic Linking

ENIAC¶

• History

Entropy¶

• Information

Event Loop¶

• GUI 프로그램에서 Multithreading이 필요한 이유
• QThread와 QRunnable의 차이
• QThread의 wait와 GUI Thread Blocking
• QThread의 기본 사용법

Exbi¶

• SI Prefixes and IEC Binary Prefixes

F-score¶

• Performance Measures for Classifiers

F2¶

• Performance Measures for Classifiers

FAT32¶

• 파일 시스템 (File System)

FLOPS¶

• History

FND¶

• FND

FPGA¶

• Integrated Circuit

File System¶

• 파일 시스템 (File System)

Firewall¶

• Internet and Related Protocols

Flip-Flop¶

• Latch
• Register

Floppy Disk¶

• Block Device

Flynn's Taxonomy¶

• Parallel Computing

Frame¶

• MMU

GPGPU¶

• Parallel Computing

GPIO¶

• Gate Outputs
• memory 기초

GRU¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

GUI¶

• GUI 프로그램에서 Multithreading이 필요한 이유
• GUI 프로그램에서 Process와 Thread
• PySide6 Dialog 기본 코드
• QCheckBox Widget
• QComboBox Widget
• QFileDialog로 file과 directory 선택하기
• QGroupBox Widget
• QInputDialog
• QLabel Widget
• QLineEdit Widget
• QPushButton Widget
• QRadioButton Widget
• QThread와 QRunnable의 차이
• QThread의 wait와 GUI Thread Blocking
• QThread의 기본 사용법
• QWidget Class
• QtCore 모듈 - Qt Class
• QtGui 모듈 - QFont, QPixmap
• Widget (위젯) 개요

Gate¶

• Boolean Algebra
• Gate에 대해서
• Integrated Circuit
• Propagation Delay

Gibi¶

• SI Prefixes and IEC Binary Prefixes

Glitch¶

• Gate에 대해서
• Noise와 싸우기

Glorot initialization¶

• Weight Initialization

Grid Computing¶

• Parallel Computing

HDD¶

• Block Device

HDL¶

• Integrated Circuit

HPC¶

• Parallel Computing

HTTP¶

• Internet and Related Protocols

Harvard-architecture¶

• Computer Architecture
• History

He initialization¶

• Weight Initialization

Hexdecimal¶

• Numeral System

Hinge Loss¶

• Perceptron Loss, Weight Update, SGD, and SVM

Hysteresis¶

• Noise와 싸우기

IC¶

• Integrated Circuit

IEEE754¶

• Real Number

IRQ¶

• Interrupt and Polling
• Push Btns

ISR¶

• Interrupt and Polling

Imperative¶

• Declarative Programming Language vs. Imperative Programming Language

Information¶

• Information

Internet¶

• Internet and Related Protocols

Interrupt¶

• Interrupt and Polling
• Push Btns

Isochronous¶

• USB

J. McCarthy¶

• 참고자료 : AI의 시작 ...

Jacobian¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

Kaiming initialization¶

• Weight Initialization

Kibi¶

• SI Prefixes and IEC Binary Prefixes

LD_LIBRARY_PATH¶

• gcc: Dynamic Linking

LRU¶

• Virtual Memory

LSB¶

• MSB and LSB

LSI¶

• History
• Integrated Circuit

LSTM¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

Laptop¶

• 컴퓨터 분류.

Latch¶

• Latch

LeCun initialization¶

• Weight Initialization

Linear Models¶

• Perceptron과 Linear Regression, Logistic Regression 의 차이

Linear Regression¶

• Perceptron과 Linear Regression, Logistic Regression 의 차이

Lithography¶

• Integrated Circuit

Log¶

• Information

Logistic Regression¶

• Perceptron과 Linear Regression, Logistic Regression 의 차이

Luong¶

• Attention Score (or Alignment)

MCU¶

• CPU Summary

MIMD¶

• Parallel Computing

MLPRegressor¶

• MLPRegressor

MMU¶

• MMU
• Virtual Memory

MPU¶

• CPU Summary

MSB¶

• MSB and LSB

MSI¶

• Integrated Circuit

Machine Learning¶

• Perceptron Loss, Weight Update, SGD, and SVM
• Perceptron과 Linear Regression, Logistic Regression 의 차이

Mainframe¶

• 컴퓨터 분류.

McCulloch-Pitts-neuron¶

• Early Artificial Neural Networks

Mebi¶

• SI Prefixes and IEC Binary Prefixes

Memory¶

• MMU
• memory 기초

Memory Latency¶

• memory 기초

Microcomputer¶

• 컴퓨터 분류.

Microprocessor¶

• History

Mini-computer¶

• 컴퓨터 분류.

Modified-Harvard-architecture¶

• Computer Architecture

Multiplex¶

• IO Mux

Multiprocessing¶

• GUI 프로그램에서 Process와 Thread

Multiprocessor¶

• Parallel Computing

Multithreading¶

• GUI 프로그램에서 Multithreading이 필요한 이유
• GUI 프로그램에서 Process와 Thread
• QThread와 QRunnable의 차이
• QThread의 wait와 GUI Thread Blocking
• QThread의 기본 사용법

Mux¶

• memory 기초

NAG¶

• NAdam

NAND Flash¶

• Flash Memory

NOR Flash¶

• Flash Memory

NTFS¶

• 파일 시스템 (File System)

Neural Network¶

• Recurrent Neural Network

OS¶

• MMU
• OS
• 파일 시스템 (File System)

Octal¶

• Numeral System

Open-Collector¶

• Gate Outputs
• Open-Collector Output

Open-Drain¶

• Open-Collector Output

Operating System¶

• Interrupt and Polling

Optical Disc¶

• Block Device

PC¶

• History
• 컴퓨터 분류.

PDP-8¶

• History

POSIX¶

• Potability and POSIX

PR¶

• Performance Measures for Classifiers

PWM¶

• Duty Cycle

Page¶

• MMU

Page Fault¶

• Virtual Memory

Page Replacement¶

• Virtual Memory

Paradigm¶

• Declarative Programming Language vs. Imperative Programming Language

Parallel Computing¶

• Parallel Computing

Passive Pullupm¶

• Gate Outputs

Pebi¶

• SI Prefixes and IEC Binary Prefixes

Perceptron¶

• Perceptron Loss, Weight Update, SGD, and SVM
• Perceptron과 Linear Regression, Logistic Regression 의 차이

Physical Memory¶

• Virtual Memory

Pin¶

• IO Ports

Polling¶

• Interrupt and Polling

Port¶

• Port

Process¶

• GUI 프로그램에서 Process와 Thread
• Process and Thread

Processor¶

• CPU Summary

Programming¶

• Declarative Programming Language vs. Imperative Programming Language

Propagation Delay¶

• Propagation Delay

Pull-Up Resistor¶

• Open-Collector Output

Pull-up¶

• Push Btns

PyQt¶

• GUI 프로그램에서 Multithreading이 필요한 이유
• GUI 프로그램에서 Process와 Thread
• QThread와 QRunnable의 차이
• QThread의 wait와 GUI Thread Blocking
• QThread의 기본 사용법

PyQt6¶

• Custom Signal 만들기
• QCheckBox Widget
• QComboBox Widget
• QGroupBox Widget
• QLabel Widget
• QLineEdit Widget
• QPushButton Widget
• QRadioButton Widget
• QWidget Class
• Qt Event Handling 구현 및 예제
• Qt Event와 Event Handling
• QtCore 모듈 - Qt Class
• QtGui 모듈 - QFont, QPixmap
• Signals and Slots 예제 (Connection Type별)
• Widget (위젯) 개요

PySide6¶

• Custom Signal 만들기
• GUI 프로그램에서 Multithreading이 필요한 이유
• GUI 프로그램에서 Process와 Thread
• PySide6 Dialog 기본 코드
• QCheckBox Widget
• QComboBox Widget
• QFileDialog로 file과 directory 선택하기
• QGroupBox Widget
• QInputDialog
• QLabel Widget
• QLineEdit Widget
• QPushButton Widget
• QRadioButton Widget
• QRunnable과 QThreadPool
• QThread와 QRunnable의 차이
• QThread의 wait와 GUI Thread Blocking
• QThread의 기본 사용법
• QWidget Class
• Qt Event Handling 구현 및 예제
• Qt Event와 Event Handling
• QtCore 모듈 - Qt Class
• QtGui 모듈 - QFont, QPixmap
• Signals and Slots 예제 (Connection Type별)
• Widget (위젯) 개요

Python¶

• QFileDialog로 file과 directory 선택하기
• QInputDialog

QAbstractButton¶

• QPushButton Widget

QApplication¶

• Empty Window Example
• QApplication

QButtonGroup¶

• QCheckBox Widget
• QGroupBox Widget
• QRadioButton Widget

QCheckBox¶

• QCheckBox Widget

QCloseEvent¶

• Qt Event Handling 구현 및 예제

QComboBox¶

• QComboBox Widget

QDialog¶

• PySide6 Dialog 기본 코드

QEvent¶

• Qt Event와 Event Handling

QFileDialog¶

• QFileDialog로 file과 directory 선택하기

QFont¶

• QtGui 모듈 - QFont, QPixmap

QGroupBox¶

• QGroupBox Widget

QKeyEvent¶

• Qt Event Handling 구현 및 예제

QLabel¶

• Empty Window Example
• QLabel Widget

QLineEdit¶

• QLineEdit Widget

QMainWindow¶

• QMainWindow

QObject¶

• Custom Signal 만들기

QPixmap¶

• QtGui 모듈 - QFont, QPixmap

QProcess¶

• GUI 프로그램에서 Process와 Thread

QPushButton¶

• QPushButton Widget

QRadioButton¶

• QRadioButton Widget

QRunnable¶

• GUI 프로그램에서 Multithreading이 필요한 이유
• QRunnable과 QThreadPool
• QThread와 QRunnable의 차이

QThread¶

• GUI 프로그램에서 Multithreading이 필요한 이유
• GUI 프로그램에서 Process와 Thread
• QRunnable과 QThreadPool
• QThread와 QRunnable의 차이
• QThread의 wait와 GUI Thread Blocking
• QThread의 기본 사용법
• Signals and Slots 예제 (Connection Type별)

QThreadPool¶

• GUI 프로그램에서 Multithreading이 필요한 이유
• GUI 프로그램에서 Process와 Thread
• QRunnable과 QThreadPool
• QThread와 QRunnable의 차이

QWidget¶

• Empty Window Example
• QWidget Class

Qt¶

• Custom Signal 만들기
• GUI 프로그램에서 Multithreading이 필요한 이유
• GUI 프로그램에서 Process와 Thread
• PySide6 Dialog 기본 코드
• QCheckBox Widget
• QComboBox Widget
• QFileDialog로 file과 directory 선택하기
• QGroupBox Widget
• QInputDialog
• QLabel Widget
• QLineEdit Widget
• QPushButton Widget
• QRadioButton Widget
• QRunnable과 QThreadPool
• QThread와 QRunnable의 차이
• QThread의 wait와 GUI Thread Blocking
• QThread의 기본 사용법
• QWidget Class
• Qt Event Handling 구현 및 예제
• Qt Event와 Event Handling
• QtCore 모듈 - Qt Class
• QtGui 모듈 - QFont, QPixmap
• Signals and Slots 예제 (Connection Type별)
• Widget (위젯) 개요

QtCore¶

• Main Modules Summary
• QtCore 모듈 - Qt Class

QtGui¶

• Main Modules Summary
• QtGui 모듈 - QFont, QPixmap

QtWidgets¶

• Main Modules Summary

QueuedConnection¶

• Signals and Slots 예제 (Connection Type별)

RAM¶

• RAM

RAS¶

• memory 기초

RNN¶

• Recurrent Neural Network
• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem
• 연결방식으로 구분한 RNN

ROC¶

• Performance Measures for Classifiers

Radix¶

• Numeral System

Random Variable¶

• Information

Register¶

• Register
• memory 기초

Registers¶

• CPU Summary

Relay¶

• Relay

Ripple Counter¶

• Counter

Ripple-Carry¶

• Propagation Delay

SASD¶

• Block Device

SDRAM¶

• RAM

SGD¶

• Perceptron Loss, Weight Update, SGD, and SVM
• Perceptron과 Linear Regression, Logistic Regression 의 차이

SGDClassifier¶

• Perceptron Loss, Weight Update, SGD, and SVM
• Perceptron과 Linear Regression, Logistic Regression 의 차이

SIGNAL¶

• Interrupt and Polling

SIMD¶

• Parallel Computing

SPMD¶

• Parallel Computing

SRAM¶

• RAM
• Register

SSD¶

• Flash Memory

SSI¶

• Integrated Circuit

SVM¶

• Perceptron Loss, Weight Update, SGD, and SVM

Schmitt Trigger¶

• Noise와 싸우기

Scientific Notation¶

• Real Number

Segmentation¶

• MMU

Selector¶

• memory 기초

Sequential Data¶

• Recurrent Neural Network

Shared Object¶

• gcc: Dynamic Linking

Signal¶

• Custom Signal 만들기
• QRunnable과 QThreadPool
• QThread의 wait와 GUI Thread Blocking
• QThread의 기본 사용법

Significant Figures¶

• Real Number

Simple RNN¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

Slot¶

• QRunnable과 QThreadPool
• QThread의 wait와 GUI Thread Blocking
• QThread의 기본 사용법

Storage¶

• 파일 시스템 (File System)

Super Computer¶

• 컴퓨터 분류.

Super-computer¶

• History

Swapping¶

• Virtual Memory

Switch¶

• Transistor
• Vacuum Tubes

System Call¶

• Interrupt and Polling

TCP/IP¶

• Internet and Related Protocols

TRAP¶

• Interrupt and Polling

Tebi¶

• SI Prefixes and IEC Binary Prefixes

Thread¶

• GUI 프로그램에서 Multithreading이 필요한 이유
• GUI 프로그램에서 Process와 Thread
• Process and Thread
• QRunnable과 QThreadPool
• QThread와 QRunnable의 차이
• QThread의 wait와 GUI Thread Blocking
• QThread의 기본 사용법

Thunder Bolt¶

• USB

Totem-Pole¶

• Gate Outputs
• Totem-pole Output

Transistor¶

• Transistor

Tri-State¶

• memory 기초

Tri-State Output¶

• Gate Outputs
• Tri-State Output

Triode¶

• Vacuum Tubes

Tunneling¶

• USB

Turing Completeness¶

• Declarative Programming Language vs. Imperative Programming Language

USB¶

• USB

USB-C¶

• USB

USB-PD¶

• USB

VLSI¶

• History
• Integrated Circuit

Vacuum Tube¶

• Vacuum Tubes

Vaswani¶

• Attention Score (or Alignment)

Virtual Memory¶

• MMU
• Virtual Memory

Volatile¶

• RAM

WWW¶

• Internet and Related Protocols

Wear Level¶

• Flash Memory

Wired AND¶

• Gate Outputs

Workstation¶

• 컴퓨터 분류.

Xavier initialization¶

• Weight Initialization

__dict__¶

• Python의 Encapsulation

abstraction¶

• Abstraction - class, instance, object
• Object 란
• Programming Language

accuracy¶

• Performance Measures for Classifiers

activation function¶

• Hyper-Parameters in Deep Learning
• Sigmoid Linear Unit (SiLU) - from GELU to Mish
• Solutions for the Gradient Vanishing or Exploding Problem
• Weight Initialization

activation-function¶

• Early Artificial Neural Networks
• MLPRegressor
• Rectified Linear Unit (ReLU) 및 변형 활성화 함수 정리

adagrad¶

• Optimizers

adam¶

• Adam Optimizer
• AdamW Optimizer
• NAdam
• Optimizers

adamw¶

• AdamW Optimizer
• Optimizers

ai¶

• AI, ML and DL.
• 참고자료 : AI의 시작 ...

alexnet¶

• alexnet

alpha-dropout¶

• dropout

ann¶

• Early Artificial Neural Networks
• MLPRegressor
• Solutions for the Gradient Vanishing or Exploding Problem

application¶

• Computer 주요구성요소

arpanet¶

• The History of Data Communication Network

artificial-neural-network¶

• Early Artificial Neural Networks

assembler¶

• Assembly Language

assembly¶

• Assembly Language

attention¶

• Attention Score (or Alignment)

attention score¶

• Attention Score (or Alignment)

attribute¶

• Abstraction - class, instance, object
• Python의 Class (차이점)
• Python의 Encapsulation

autoencoder¶

• Unsupervised Pretraining

autograd¶

• PyTorch로 직접 구현해보는 Linear Regression

average-pooling¶

• Pooling Layer

backpropagation¶

• Early Artificial Neural Networks
• Solutions for the Gradient Vanishing or Exploding Problem

backpropagation through time¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

bagging¶

• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)
• [ML] Classic Regressor (Summary)

bash¶

• Console, Terminal, and Shell
• 명령어 (GNU/Linux)

basic-structure¶

• Empty Window Example

batch Size¶

• Batch Size

batch learning¶

• Batch Learning
• Categories of ML
• Online Learning

batch normalization¶

• Batch Normalization 정리
• Group Normalization
• Solutions for the Gradient Vanishing or Exploding Problem

batch size¶

• Hyper-Parameters in Deep Learning

behavior¶

• Abstraction - class, instance, object

bernoulli-distribution¶

• Logistic Regression

binary-classification¶

• Logistic Regression
• Types of Classification

binary-cross-entropy¶

• Logistic Regression

bit¶

• Units for bit.

bluetooth¶

• Ethernet, Router, Switch and so on

bn¶

• Batch Normalization 정리

boosting¶

• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)
• [ML] Classic Regressor (Summary)

bottleneck¶

• DenseNet의 구조와 특징

bound-method¶

• Python의 Class (차이점)

built-in¶

• Python zip() Function

builtin¶

• Console, Terminal, and Shell

bytecode¶

• Compiler vs Interpreter

bytes¶

• Units for bit.

c¶

• Compiler vs Interpreter

c++¶

• Compiler vs Interpreter

cache¶

• Memory Hierarchy and Cache

cache coherence¶

• Memory Hierarchy and Cache

cache hit¶

• Memory Hierarchy and Cache

cache miss¶

• Memory Hierarchy and Cache

calculator¶

• What is a Computer?

callback¶

• OpenCV-Basic03

categorical distribution¶

• Categorical distribution에서 Cross entropy loss 유도

categorical-distribution¶

• Logistic Regression

ccr¶

• Overflow and Underflow

centos¶

• 리눅스 (GNU/Linux)

central-widget¶

• QMainWindow

cfs¶

• Process Scheduling

chain rule¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

checkpoint¶

• Early Stopping

class¶

• Abstraction - class, instance, object
• Inheritance
• Python의 Class (차이점)

classification¶

• Categorical distribution에서 Cross entropy loss 유도
• Perceptron and MLPClassifier
• Types of Classification
• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)

cli¶

• Console, Terminal, and Shell
• User Interface
• 명령어 (GNU/Linux)

clip_grad_norm_¶

• Gradient Clipping

clip_grad_value_¶

• Gradient Clipping

clock¶

• Oscillator

close¶

• Qt Event Handling 구현 및 예제

clustering¶

• Unsupervised Learning

cnn¶

• Convolutional Layer
• DenseNet의 구조와 특징
• Group Normalization
• Pooling Layer
• PyTorch의 nn.Conv2d 사용법
• alexnet

colab¶

• Colab
• Colab : Hotkeys

color space¶

• Color Space (or Color Model)
• OpenCV-Basic01

compiler¶

• Compiler vs Interpreter

computer¶

• What is a Computer?

computer vision¶

• ResNet: Deep Residual Learning for Image Recognition (2015)
• alexnet

confusion matrix¶

• Performance Measures for Classifiers

connect¶

• Signals and Slots 예제 (Connection Type별)

console¶

• Console, Terminal, and Shell

container¶

• container and vm

contrast-enhancement¶

• Histogram-based Image Processing Techniques

control¶

• Widget (위젯) 개요

control structure¶

• Programming Language

conv2d¶

• PyTorch의 nn.Conv2d 사용법

convolution¶

• Convolution
• Convolutional Layer
• PyTorch의 nn.Conv2d 사용법

coprocessor¶

• Coprocessor

cpp¶

• Abstraction - class, instance, object

cpu¶

• Computer 주요구성요소

critical batch size¶

• Batch Size

cross entropy¶

• Categorical distribution에서 Cross entropy loss 유도

cross-entropy¶

• Logistic Regression

custom signal¶

• Custom Signal 만들기

custom-dialog¶

• QDialog

cv2.circle¶

• OpenCV-Basic02

cv2.imread¶

• OpenCV-Basic01

cv2.imshow¶

• OpenCV-Basic01

cv2.imwrite¶

• OpenCV-Basic01

cv2.line¶

• OpenCV-Basic02

cv2.rectangle¶

• OpenCV-Basic02

cv2.setMouseCallback¶

• OpenCV-Basic03

data¶

• Data Representation

data hiding¶

• Python의 Encapsulation

data-communication¶

• The History of Data Communication Network

dbn¶

• Unsupervised Pretraining

debian¶

• 리눅스 (GNU/Linux)

decision tree¶

• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)

deep learning¶

• Batch Normalization 정리
• Gradient Clipping
• Group Normalization
• Hyper-Parameters in Deep Learning
• Learning Rate Tuning and Scheduling
• Sigmoid Linear Unit (SiLU) - from GELU to Mish
• Solutions for the Gradient Vanishing or Exploding Problem
• Unsupervised Pretraining
• alexnet

deep-learning¶

• DL Framework와 GPGPU 가속 기술
• Early Artificial Neural Networks
• Logistic Regression
• Memory Cell (or Cell)
• Momentum
• Pooling Layer
• Why Use Machine Learning

dense-connectivity¶

• DenseNet의 구조와 특징

dense-layer¶

• DenseNet의 구조와 특징

densenet¶

• DenseNet의 구조와 특징

densenet-121¶

• DenseNet의 구조와 특징

descriptor¶

• Python의 Class (차이점)

design-principle¶

• Good User Interface

dialog¶

• QDialog
• QMessageBox 기본 사용법
• QMessageBox 예제 코드
• Window and Dialog
• Window and Dialog

diamond-problem¶

• Inheritance

diffusion model¶

• Unsupervised Pretraining

dilation¶

• PyTorch의 nn.Conv2d 사용법

dir¶

• Python의 Encapsulation

dispatcher¶

• Memory Hierarchy and Cache
• Process Scheduling

distributions¶

• 리눅스 (GNU/Linux)

dl¶

• AI, ML and DL.
• Early Artificial Neural Networks

dl-framework¶

• DL Framework와 GPGPU 가속 기술

dma¶

• Coprocessor

docker¶

• container and vm

double¶

• Real Number

downsampling¶

• Pooling Layer

dropout¶

• alexnet
• dropout

dynamic linking¶

• Library, Shared Library, Dynamic Linking

early-stopping¶

• Early Stopping
• MLPRegressor

emit¶

• Custom Signal 만들기

encapsulation¶

• Python의 Encapsulation

encoder-decoder¶

• Attention Score (or Alignment)
• 연결방식으로 구분한 RNN

engine¶

• Web Browser

ensemble¶

• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)
• [ML] Classic Regressor (Summary)

entry point¶

• Library, Shared Library, Dynamic Linking

enum¶

• QtCore 모듈 - Qt Class

ethernet¶

• Ethernet, Router, Switch and so on

event¶

• Qt Event Handling 구현 및 예제
• Qt Event와 Event Handling

event handler¶

• Qt Event Handling 구현 및 예제

event handling¶

• Qt Event Handling 구현 및 예제
• Qt Event와 Event Handling

event loop¶

• Qt Event Handling 구현 및 예제
• Qt Event와 Event Handling

event-loop¶

• QApplication

exFAT¶

• 파일 시스템 (File System)

executable file¶

• Library, Shared Library, Dynamic Linking

explicit-programming¶

• Why Use Machine Learning

exploding gradient¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

ext4¶

• 파일 시스템 (File System)

family¶

• History

fan in¶

• Weight Initialization

fan out¶

• Weight Initialization

fcfs¶

• Process Scheduling

feature-engineering¶

• FE: Categorical Feature Combination
• FE: Target Encoding (or Mean Encoding, Response Encoding)

feature-reuse¶

• DenseNet의 구조와 특징

field¶

• Units for bit.

filter¶

• Convolution

float¶

• Real Number

forward pass¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

gan¶

• Unsupervised Pretraining

gcc¶

• gcc: Dynamic Linking
• gcc: Static Linking

gd¶

• Optimizers

gelu¶

• Sigmoid Linear Unit (SiLU) - from GELU to Mish

getter¶

• Python의 Encapsulation

global-average-pooling¶

• Pooling Layer

glu¶

• Sigmoid Linear Unit (SiLU) - from GELU to Mish

gnu¶

• 리눅스 (GNU/Linux)

gnu/linux¶

• UNIX

gpgpu¶

• DL Framework와 GPGPU 가속 기술

gpu¶

• GPU and TPU

gpu-acceleration¶

• DL Framework와 GPGPU 가속 기술

gradient¶

• Adam Optimizer
• AdamW Optimizer
• Optimizers

gradient accumulation¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

gradient clipping¶

• Gradient Clipping
• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem
• Solutions for the Gradient Vanishing or Exploding Problem

gradient descent¶

• PyTorch로 직접 구현해보는 Linear Regression

gradient exploding¶

• Batch Normalization 정리
• Gradient Clipping
• Solutions for the Gradient Vanishing or Exploding Problem
• Weight Initialization

gradient norm¶

• Gradient Clipping

gradient value¶

• Gradient Clipping

gradient vanishing¶

• Batch Normalization 정리
• Gradient Clipping
• Solutions for the Gradient Vanishing or Exploding Problem
• Weight Initialization

gradient-descent¶

• Momentum

greedy layerwise learning¶

• Semi-supervised Learning

group normalization¶

• Group Normalization

growth-rate¶

• DenseNet의 구조와 특징

gui¶

• Chapter 00. Introduction
• PyQt and PySide Overview
• QApplication
• QMainWindow
• QMessageBox 예제 코드
• User Interface

hardware¶

• Computer 주요구성요소

hdr¶

• gcc: Static Linking

he-initialization¶

• Rectified Linear Unit (ReLU) 및 변형 활성화 함수 정리

header¶

• gcc: Static Linking

hebbian-learning¶

• Early Artificial Neural Networks

hidden layer¶

• MLPRegressor

hidden-state¶

• Memory Cell (or Cell)

hierarchy¶

• Inheritance

high-level language¶

• Programming Language

histogram¶

• Histogram
• Histogram-based Image Processing Techniques

history¶

• Early Artificial Neural Networks
• The History of Data Communication Network
• UNIX
• 참고자료 : AI의 시작 ...

hotkeys¶

• Colab : Hotkeys

hyperparameter¶

• Hyper-Parameters in Deep Learning
• Learning Rate Tuning and Scheduling
• MLPRegressor
• ML의 주요 단계와 성공을 위해 고려해야하는 요소

i/o¶

• Computer 주요구성요소

ieee 802.11¶

• Ethernet, Router, Switch and so on

ilsvrc¶

• alexnet

image classification¶

• ResNet: Deep Residual Learning for Image Recognition (2015)

image processing¶

• Histogram

image-classification¶

• DenseNet의 구조와 특징

image-processing¶

• Histogram-based Image Processing Techniques
• Image Thresholding

image-segmentation¶

• Histogram-based Image Processing Techniques

imagenet¶

• alexnet

import¶

• Python Module and Package

incremental learning¶

• Batch Learning
• Categories of ML
• Online Learning

index register¶

• Index Register and Relative Addressing

inductive learning¶

• Categories of ML

information¶

• Data Representation

inheritance¶

• Inheritance

instance¶

• Abstraction - class, instance, object

instance based learning¶

• Categories of ML

instruction¶

• Data Representation

interface¶

• User Interface

internal covariate shift¶

• Batch Normalization 정리

interpreter¶

• Compiler vs Interpreter

introduction¶

• Chapter 00. Introduction

ipynb¶

• Colab

ipython¶

• Colab

iterable¶

• Python zip() Function

iterator¶

• Python zip() Function

java¶

• Compiler vs Interpreter

javascript¶

• Compiler vs Interpreter

jupyter¶

• Colab

keras¶

• Momentum

kernel¶

• Console, Terminal, and Shell
• Convolution
• Kernel
• 리눅스 (GNU/Linux)

lan¶

• Ethernet, Router, Switch and so on
• The History of Data Communication Network

large batch¶

• Batch Size

layer¶

• Hyper-Parameters in Deep Learning

layer normalization¶

• Batch Normalization 정리
• Group Normalization

layout¶

• QMainWindow

leaky-relu¶

• Rectified Linear Unit (ReLU) 및 변형 활성화 함수 정리

learning rate¶

• Learning Rate Tuning and Scheduling

learning rate scaling¶

• Batch Size

library¶

• Library, Shared Library, Dynamic Linking

linear regression¶

• PyTorch로 직접 구현해보는 Linear Regression

linker¶

• Library, Shared Library, Dynamic Linking

linux¶

• UNIX
• 리눅스 (GNU/Linux)
• 명령어 (GNU/Linux)

local derivative¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

logistic regression¶

• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)

logistic-regression¶

• Logistic Regression

long-term dependency¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

loss-curve¶

• MLPRegressor

low-level language¶

• Programming Language

low-level-language¶

• Assembly Language

mAP¶

• Performance Measures for Classifiers

machine¶

• What is a Computer?

machine learning¶

• Batch Learning
• Categorical distribution에서 Cross entropy loss 유도
• Categories of ML
• Online Learning
• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)
• train_test_split 사용하기

machine-code¶

• Assembly Language
• Compiler vs Interpreter

machine-learning¶

• Logistic Regression
• Momentum
• Why Use Machine Learning
• [ML] Classic Regressor (Summary)

macro¶

• Performance Measures for Classifiers

mainframe¶

• History

many-to-many¶

• 연결방식으로 구분한 RNN

many-to-one¶

• 연결방식으로 구분한 RNN

max-norm¶

• Max-Norm Regularization

max-pooling¶

• Pooling Layer

maximum-likelihood-estimation¶

• Logistic Regression

mc-dropout¶

• dropout

memory¶

• Computer 주요구성요소

memory-cell¶

• Memory Cell (or Cell)

metaclass¶

• Python의 Class (차이점)

method¶

• Python의 Class (차이점)

micro¶

• Performance Measures for Classifiers

mini-batch¶

• Online Learning

mini-batch gd¶

• Batch Size

minicomputer¶

• History

mish¶

• Sigmoid Linear Unit (SiLU) - from GELU to Mish

ml¶

• AI, ML and DL.
• Why Use Machine Learning
• [ML] Classic Regressor (Summary)

mlp¶

• Early Artificial Neural Networks
• MLPRegressor
• Perceptron and MLPClassifier

mlpclassifier¶

• Perceptron and MLPClassifier

mnemonic¶

• Assembly Language

modal¶

• QDialog
• Window and Dialog

model based learning¶

• Categories of ML

modeless¶

• QDialog
• Window and Dialog

modem¶

• The History of Data Communication Network

module¶

• Main Modules Summary
• Python Module and Package

moment¶

• AdamW Optimizer

momentum¶

• Adam Optimizer
• Momentum
• Optimizers

moveToThread¶

• QRunnable과 QThreadPool

mro¶

• Inheritance

mse¶

• PyTorch로 직접 구현해보는 Linear Regression

multi-class classification¶

• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)

multi-label classification¶

• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)

multiLayer-perceptron¶

• Early Artificial Neural Networks

multiclass-classification¶

• Types of Classification

multilabel-classification¶

• Types of Classification

multilayer-perceptron¶

• MLPRegressor

multioutput-classification¶

• Types of Classification

multiple-inheritance¶

• Inheritance

na¶

• Optimizers

nadam¶

• Optimizers

nag¶

• Optimizers

name mangling¶

• Python의 Encapsulation

namespace-package¶

• Python Module and Package

negative log-likelihood¶

• Categorical distribution에서 Cross entropy loss 유도

negative-log-likelihood¶

• Logistic Regression

neural network¶

• MLPRegressor
• Solutions for the Gradient Vanishing or Exploding Problem

neuron¶

• Hyper-Parameters in Deep Learning

non-preemptive¶

• Process Scheduling

normalization¶

• Group Normalization

notebook¶

• Colab

novelty¶

• Unsupervised Learning

numpy¶

• Histogram

object¶

• Abstraction - class, instance, object
• Inheritance
• Object 란
• Python의 Class (차이점)
• Python의 Encapsulation
• gcc: Static Linking

object file¶

• Library, Shared Library, Dynamic Linking

offline learning¶

• Batch Learning

one-to-many¶

• 연결방식으로 구분한 RNN

one-to-one¶

• 연결방식으로 구분한 RNN

online learning¶

• Batch Learning
• Categories of ML
• Online Learning

oop¶

• Abstraction - class, instance, object
• Object 란

opencv¶

• Histogram
• Image Thresholding

operation¶

• Data Representation

optimization¶

• Gradient Clipping
• Learning Rate Tuning and Scheduling
• Momentum
• Optimizers
• PyTorch로 직접 구현해보는 Linear Regression

optimizer¶

• Adam Optimizer
• AdamW Optimizer
• Hyper-Parameters in Deep Learning
• NAdam
• Optimizers

os¶

• Console, Terminal, and Shell
• Kernel
• UNIX
• 리눅스 (GNU/Linux)
• 명령어 (GNU/Linux)

oscillator¶

• Oscillator

osi¶

• The History of Data Communication Network

out-of-core learning¶

• Online Learning

outlier¶

• Unsupervised Learning

overfit¶

• ML의 주요 단계와 성공을 위해 고려해야하는 요소

overfitting¶

• Early Stopping

overflow¶

• Overflow and Underflow

overriding¶

• Inheritance

ovo¶

• Types of Classification

ovr¶

• Types of Classification

package¶

• Package Management
• Python Module and Package

paintEvent¶

• Qt Event Handling 구현 및 예제

parameter sharing¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

perceptron¶

• Early Artificial Neural Networks
• Perceptron and MLPClassifier

pooling¶

• Pooling Layer

portability¶

• Potability and POSIX

porting¶

• Potability and POSIX

precision¶

• Performance Measures for Classifiers

preemptive¶

• Process Scheduling

prelu¶

• Rectified Linear Unit (ReLU) 및 변형 활성화 함수 정리

program¶

• What is a Computer?

programming¶

• Programming Language

propagation delay¶

• Oscillator

property¶

• Python의 Encapsulation

protocol¶

• The History of Data Communication Network

pulse¶

• Oscillator

pyqt¶

• QMessageBox 기본 사용법
• QMessageBox 예제 코드

pyqt6¶

• Chapter 00. Introduction
• Empty Window Example
• Main Modules Summary
• PyQt and PySide Overview
• QApplication
• QDialog
• QMainWindow
• QtWidgets Module Overview
• User Interface
• Window and Dialog
• Window and Dialog

pyqtSignal¶

• Custom Signal 만들기

pyside6¶

• Chapter 00. Introduction
• Empty Window Example
• Main Modules Summary
• PyQt and PySide Overview
• QApplication
• QDialog
• QMainWindow
• QMessageBox 기본 사용법
• QMessageBox 예제 코드
• QtWidgets Module Overview
• User Interface
• Window and Dialog
• Window and Dialog

python¶

• Abstraction - class, instance, object
• Compiler vs Interpreter
• Object 란
• Python Module and Package
• Python zip() Function
• Python의 Class (차이점)
• QMessageBox 기본 사용법
• QMessageBox 예제 코드

python-binding¶

• PyQt and PySide Overview

pytorch¶

• Early Stopping
• Gradient Clipping
• Group Normalization
• Max-Norm Regularization
• Momentum
• PyTorch nn.RNNCell and nn.RNN
• PyTorch로 직접 구현해보는 Linear Regression
• PyTorch의 nn.Conv2d 사용법
• dropout

qapplication¶

• QtWidgets Module Overview
• Window and Dialog

qdialog¶

• QDialog
• Window and Dialog
• Window and Dialog

qlabel¶

• QtWidgets Module Overview

qmainwindow¶

• Window and Dialog
• Window and Dialog

qmessagebox¶

• QMessageBox 기본 사용법
• QMessageBox 예제 코드

qt¶

• PyQt and PySide Overview
• QMessageBox 예제 코드

qtwidgets¶

• QtWidgets Module Overview

queue¶

• Process Scheduling

qwidget¶

• QtWidgets Module Overview

random forest¶

• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)

random-forest¶

• [ML] Classic Regressor (Summary)

rbm¶

• Unsupervised Pretraining

recall¶

• Performance Measures for Classifiers

record¶

• Units for bit.

recurrent-Layer¶

• Memory Cell (or Cell)

recurrent-neural-network¶

• Memory Cell (or Cell)
• PyTorch nn.RNNCell and nn.RNN

recurrent-neuron¶

• Memory Cell (or Cell)

redhat¶

• 리눅스 (GNU/Linux)

regression¶

• MLPRegressor
• [ML] Classic Regressor (Summary)

regularization¶

• Batch Normalization 정리
• Early Stopping
• Group Normalization
• MLPRegressor
• ML의 주요 단계와 성공을 위해 고려해야하는 요소
• Max-Norm Regularization
• dropout

reinforcement learning¶

• Categories of ML

relocation¶

• Library, Shared Library, Dynamic Linking

relu¶

• Rectified Linear Unit (ReLU) 및 변형 활성화 함수 정리
• Sigmoid Linear Unit (SiLU) - from GELU to Mish
• alexnet

representation¶

• AI, ML and DL.

representation Learning¶

• AI, ML and DL.

representation learning¶

• Unsupervised Pretraining

residual learning¶

• ResNet: Deep Residual Learning for Image Recognition (2015)

resnet¶

• ResNet: Deep Residual Learning for Image Recognition (2015)

rf¶

• [ML] Classic Regressor (Summary)

rmspro¶

• Optimizers

rmsprop¶

• Adam Optimizer

rnn¶

• Gradient Clipping
• Memory Cell (or Cell)
• PyTorch nn.RNNCell and nn.RNN

rnn-cell¶

• PyTorch nn.RNNCell and nn.RNN

round-robin¶

• Process Scheduling

router¶

• Ethernet, Router, Switch and so on

rrelu¶

• Rectified Linear Unit (ReLU) 및 변형 활성화 함수 정리

rule-based-ai¶

• Why Use Machine Learning

runtime library¶

• Library, Shared Library, Dynamic Linking

scikit-learn¶

• MLPRegressor
• Perceptron and MLPClassifier
• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)
• [ML] Classic Regressor (Summary)
• train_test_split 사용하기

self-supervised learning¶

• Categories of ML
• Unsupervised Pretraining

semi-supervised learning¶

• Categories of ML
• Unsupervised Pretraining

semisupervised¶

• Semi-supervised Learning

sensitivity¶

• Performance Measures for Classifiers

seq2seq¶

• Attention Score (or Alignment)
• 연결방식으로 구분한 RNN

seq2vec¶

• 연결방식으로 구분한 RNN

setter¶

• Python의 Encapsulation

sgd¶

• Batch Size
• Momentum

shared library¶

• Library, Shared Library, Dynamic Linking

shell¶

• Console, Terminal, and Shell
• 명령어 (GNU/Linux)

shortcut connection¶

• ResNet: Deep Residual Learning for Image Recognition (2015)

shortcuts¶

• Colab : Hotkeys

signal¶

• Custom Signal 만들기
• QCheckBox Widget
• QComboBox Widget
• QGroupBox Widget
• QLineEdit Widget
• QPushButton Widget
• QRadioButton Widget
• Qt Event와 Event Handling
• Signals and Slots 예제 (Connection Type별)

silu¶

• Sigmoid Linear Unit (SiLU) - from GELU to Mish

similarity¶

• Attention Score (or Alignment)

simula-67¶

• Object 란

single-layer-perceptron¶

• Early Artificial Neural Networks

skip connection¶

• ResNet: Deep Residual Learning for Image Recognition (2015)

slot¶

• Custom Signal 만들기
• QCheckBox Widget
• QComboBox Widget
• QGroupBox Widget
• QLineEdit Widget
• QPushButton Widget
• QRadioButton Widget
• Qt Event와 Event Handling
• Signals and Slots 예제 (Connection Type별)

slp¶

• Early Artificial Neural Networks
• Perceptron and MLPClassifier

so¶

• gcc: Dynamic Linking

softmax¶

• Categorical distribution에서 Cross entropy loss 유도
• Logistic Regression

software¶

• Computer 주요구성요소

solver¶

• MLPRegressor

spam-filter¶

• Why Use Machine Learning

static linker¶

• Library, Shared Library, Dynamic Linking

stochastic gradient descent¶

• Optimizers

stored-program-computer¶

• Computer Architecture
• History

stratified sampling¶

• train_test_split 사용하기

stride¶

• Convolutional Layer

subclass¶

• Inheritance

super¶

• Inheritance

superclass¶

• Inheritance

supervised learning¶

• Categories of ML

support vector machine¶

• [ML] Classic Classifier (Summary)
• [ML] Classic Classifier (Summary)

support-vector-machine¶

• [ML] Classic Regressor (Summary)

svm¶

• [ML] Classic Regressor (Summary)

swish¶

• Sigmoid Linear Unit (SiLU) - from GELU to Mish

switching¶

• Ethernet, Router, Switch and so on
• The History of Data Communication Network

symbol resolution¶

• Library, Shared Library, Dynamic Linking

synchronous¶

• Oscillator

system-sw¶

• Computer 주요구성요소

tcp/ip¶

• The History of Data Communication Network

terminal¶

• Console, Terminal, and Shell

thresholding¶

• Image Thresholding

time slice¶

• Index Register and Relative Addressing

topology¶

• 연결방식으로 구분한 RNN

torch¶

• PyTorch nn.RNNCell and nn.RNN

tpu¶

• GPU and TPU

train_test_split¶

• train_test_split 사용하기

training¶

• Learning Rate Tuning and Scheduling

training stability¶

• Gradient Clipping
• Solutions for the Gradient Vanishing or Exploding Problem

transductive learning¶

• Categories of ML

transfer learning¶

• Unsupervised Pretraining

transformer¶

• AdamW Optimizer
• Attention Score (or Alignment)
• Group Normalization

transition-layer¶

• DenseNet의 구조와 특징

translation-invariance¶

• Pooling Layer

tty¶

• Console, Terminal, and Shell

type¶

• Python의 Class (차이점)

ubuntu¶

• 리눅스 (GNU/Linux)

ui¶

• Good User Interface

underfit¶

• ML의 주요 단계와 성공을 위해 고려해야하는 요소

underflow¶

• Overflow and Underflow

unix¶

• UNIX

unsupervised learning¶

• Categories of ML
• Unsupervised Pretraining

unsupervised pretraining¶

• Unsupervised Pretraining

update¶

• Qt Event Handling 구현 및 예제

usenet¶

• The History of Data Communication Network

user-interface¶

• Good User Interface
• User Interface

user-space¶

• Kernel

uucp¶

• The History of Data Communication Network

ux¶

• Good User Interface

validation¶

• ML의 주요 단계와 성공을 위해 고려해야하는 요소

validation-loss¶

• Early Stopping

vanishing gradient¶

• Simple RNN의 Forward Pass, BPTT, 그리고 Long-term Dependency Problem

variance¶

• Weight Initialization

virtual machine¶

• container and vm

virtualization¶

• container and vm

visualization¶

• Unsupervised Learning

vm¶

• What is a Computer?
• container and vm

von Neumann-architecture¶

• Computer Architecture

von-Neumann¶

• History

vruntime]¶

• Process Scheduling

wait¶

• QThread의 wait와 GUI Thread Blocking

wan¶

• The History of Data Communication Network

warmup¶

• Batch Size

web browser¶

• Web Browser

weight initialization¶

• Solutions for the Gradient Vanishing or Exploding Problem
• Weight Initialization

weight-constraint¶

• Max-Norm Regularization

weight-decay¶

• AdamW Optimizer

weighted¶

• Performance Measures for Classifiers

wi-fi¶

• Ethernet, Router, Switch and so on

widget¶

• QCheckBox Widget
• QComboBox Widget
• QGroupBox Widget
• QLabel Widget
• QLineEdit Widget
• QPushButton Widget
• QRadioButton Widget
• QWidget Class
• QtCore 모듈 - Qt Class
• QtGui 모듈 - QFont, QPixmap
• Widget (위젯) 개요

window¶

• Window and Dialog
• Window and Dialog

word¶

• Units for bit.

write back¶

• Memory Hierarchy and Cache

write through¶

• Memory Hierarchy and Cache

zip¶

• Python zip() Function

zsh¶

• Console, Terminal, and Shell

{{tags}}