You are reading immutable version 2. 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

Overview of Deep Residual Learning

Deep Residual Learning Overview

Lesson

Mathematical Formulation and Shortcut Connections

Mathematical Formulation and Shortcut Connections

Mathematical Formulation

Lesson

Identity Shortcut Connection

Mathematical Formulation and Shortcut Connections

This equation defines the fundamental identity shortcut connection in Deep Residual Learning. Instead of forcing stacked layers to directly fit a desired underlying mapping, the network is reformulated to let these layers fit a residual mapping mathcal F ( mathbf x , W i ) . The original input mathbf x is added directly to the output of the residual function via a shortcut connection.

Lesson

Projection Shortcut Connection

Mathematical Formulation and Shortcut Connections

This equation defines a residual block with a projection shortcut connection. When the input dimension of mathbf x differs from the output dimension of the residual function mathcal F , a linear projection matrix W s is applied to the input mathbf x to match the dimensions before addition.

Lesson

The Bottleneck Building Block Design

ResNet Architectures and Bottleneck Designs

The Bottleneck Design for Deeper ResNets

Lesson

Empirical Analysis of Layer Responses and Extreme Depth

Empirical Analysis and Layer Responses

Empirical Analysis of Layer Responses

Lesson

Standard deviations of layer responses on CIFAR-10

Empirical Analysis and Layer Responses

An analysis of the standard deviations (std) of layer responses on CIFAR-10 is presented in Figure 7. The responses are measured at the outputs of each 3 times3 layer, after Batch Normalization (BN) and before the nonlinearity. The results show that residual networks (ResNets) generally have smaller response standard deviations compared to their plain counterparts, supporting the hypothesis that residual functions are closer to zero than non-residual functions.

Quiz

Test your understanding

Comprehensive Assessment

14 questions grounded in this paper section.