You are reading immutable version 1. The current guide may be newer.

Study the paper

Deep Residual Learning for Image Recognition

Lessons, visuals, quizzes, flashcards, and resources—organized in teaching order.

8 activities

Lesson

At a glance

Course Overview: Deep Residual Learning

Course Overview: Deep Residual Learning

Lesson

The Degradation Problem and Optimization Difficulties

The Degradation Problem and Optimization Difficulties

Understanding the Degradation Problem

Lesson

The Degradation Problem and Residual Learning Context

The Degradation Problem and Optimization Difficulties

The Degradation Problem in Deep Networks

Lesson

Residual Block with Identity Shortcut

Mathematical Formulation of Residual Learning

This equation defines the fundamental residual block with an identity shortcut connection. The input vector is directly added to the output of the residual function, allowing gradients to flow unimpeded during backpropagation.

Lesson

Residual Block with Projection Shortcut

Identity vs. Projection Shortcuts

When the dimensions of the input mathbf x and the residual output mathcal F differ (for example, when changing channel depths), a projection shortcut W s is applied to the input to match the dimensions.

Lesson

Deeper Bottleneck Architectures Walkthrough

Deeper Bottleneck Architectures

Deeper Bottleneck Architectures

Lesson

Standard deviations of layer responses on CIFAR-10

Empirical Analysis of Layer Responses

An empirical analysis of the standard deviations (std) of layer responses on CIFAR-10 was conducted to investigate the preconditioning hypothesis. The responses are measured at the outputs of each 3 times3 layer, after Batch Normalization (BN) and before nonlinearity.

Quiz

Test your understanding

Comprehensive Assessment

12 questions grounded in this paper section.