Skip to content

d2l Julia

Main Navigation Home

📘 Chapters Overview

Linear Neural Networks for Regression

Linear Regression

Multiple Dispatch Design for Implementation

Synthetic Regression Data

Linear Regression Implementation from Scratch

Concise Implementation of Linear Regression

Generalization

Weight Decay

Linear Neural Networks for Classification

Softmax Regression

The Image Classification Dataset

Softmax Regression Implementation from Scratch

Concise Implementation of Softmax Regression

Generalization in Classification

Environment and Distribution Shift

Multilayer Perceptron

Multilayer Perceptrons

Implementation of Multilayer Perceptrons

Forward Propagation, Backward Propagation, and Computational Graphs

Numerical Stability and Initialization

Generalization in Deep Learning

Dropout

Convolutional Neural Networks

Convolutions for Images

Padding and Stride

Multiple Input and Multiple Output Channels

Pooling

Convolutional Neural Networks (LeNet)

Modern Convolutional Neural Networks

Deep Convolutional Neural Networks (AlexNet)

Networks Using Blocks (VGG)

Network in Network (NiN)

Multi-Branch Networks (GoogLeNet)

Batch Normalization

Residual Networks (ResNet) and ResNeXt

Densely Connected Networks (DenseNet)

Designing Convolution Network Architectures

Recurrent Neural Networks

Working with Sequences

Converting Raw Text into Sequence Data

Language Models

Recurrent Neural Networks

Recurrent Neural Network Implementation from Scratch

Concise Implementation of Recurrent Neural Networks

Backpropagation Through Time

Modern Recurrent Neural Networks

Long Short-Term Memory (LSTM)

Gated Recurrent Units (GRU)

Deep Recurrent Neural Networks

Bidirectional Recurrent Neural Networks

Machine Translation and the Dataset

The Encoder–Decoder Architecture

Sequence-to-Sequence Learning for Machine Translation

Attention Mechanisms and Transformers

Queries, Keys, and Values

Attention Pooling by Similarity

Attention Scoring Functions

The Bahdanau Attention Mechanism

Multi-Head Attention

Self-Attention and Positional Encoding

CH10.Attention_Mechanisms_and_Transformers/Untitled

Computer Vision

Image Augmentation

Fully Convolutional Networks

Fine-Tuning

Object Detection and Bounding Boxes

Anchor Boxes

Multiscale Object Detection

The Object Detection Dataset

Single Shot Multibox Detection

Semantic Segmentation and the Dataset

Transposed Convolution

References

Appearance

Sidebar Navigation

Home

Chapters

📘 Chapters Overview

Linear Neural Networks for Regression

Linear Regression

Multiple Dispatch Design for Implementation

Synthetic Regression Data

Linear Regression Implementation from Scratch

Concise Implementation of Linear Regression

Generalization

Weight Decay

Linear Neural Networks for Classification

Softmax Regression

The Image Classification Dataset

Softmax Regression Implementation from Scratch

Concise Implementation of Softmax Regression

Generalization in Classification

Environment and Distribution Shift

Multilayer Perceptron

Multilayer Perceptrons

Implementation of Multilayer Perceptrons

Forward Propagation, Backward Propagation, and Computational Graphs

Numerical Stability and Initialization

Generalization in Deep Learning

Dropout

Convolutional Neural Networks

Convolutions for Images

Padding and Stride

Multiple Input and Multiple Output Channels

Pooling

Convolutional Neural Networks (LeNet)

Modern Convolutional Neural Networks

Deep Convolutional Neural Networks (AlexNet)

Networks Using Blocks (VGG)

Network in Network (NiN)

Multi-Branch Networks (GoogLeNet)

Batch Normalization

Residual Networks (ResNet) and ResNeXt

Densely Connected Networks (DenseNet)

Designing Convolution Network Architectures

Recurrent Neural Networks

Working with Sequences

Converting Raw Text into Sequence Data

Language Models

Recurrent Neural Networks

Recurrent Neural Network Implementation from Scratch

Concise Implementation of Recurrent Neural Networks

Backpropagation Through Time

Modern Recurrent Neural Networks

Long Short-Term Memory (LSTM)

Gated Recurrent Units (GRU)

Deep Recurrent Neural Networks

Bidirectional Recurrent Neural Networks

Machine Translation and the Dataset

The Encoder–Decoder Architecture

Sequence-to-Sequence Learning for Machine Translation

Attention Mechanisms and Transformers

Queries, Keys, and Values

Attention Pooling by Similarity

Attention Scoring Functions

The Bahdanau Attention Mechanism

Multi-Head Attention

Self-Attention and Positional Encoding

CH10.Attention_Mechanisms_and_Transformers/Untitled

Computer Vision

Image Augmentation

Fully Convolutional Networks

Fine-Tuning

Object Detection and Bounding Boxes

Anchor Boxes

Multiscale Object Detection

The Object Detection Dataset

Single Shot Multibox Detection

Semantic Segmentation and the Dataset

Transposed Convolution

References

On this page

Multiple Dispatch Design for Implementation

julia

Edit this page

Pager

Previous pageLinear Regression

Next pageSynthetic Regression Data

Made with DocumenterVitepress.jl

Multiple Dispatch Design for Implementation ​

Multiple Dispatch Design for Implementation