Chapter 08: Neural Networks
This chapter introduces the basic concepts of neural networks. We integrated chapters from our course on Deep Learning in order to be able to use (simple) neural networks for supervised ML on tabular data.
-
Chapter 08.00: Neural Networks: In a Nutshell
In this nutshell chunk, we learn about neural networks, the driving force behind many of today’s cutting-edge machine learning applications.
-
Chapter 08.01: Introduction
In this section, we introduces the relationship of DL and ML, give basic intro about feature learning, and discuss the use-cases and data types for DL methods.
-
Chapter 08.02: Single Neuron
In this section we explain the graphical representation of a single neuron and describe affine transformations and non-linear activation functions. Moreover, we talk about the hypothesis spaces of a single neuron and name some typical loss functions.
-
Chapter 08.03: Single Hidden Layer NN
We introduce architecture of single hidden layer neural networks and discuss the advantage of hidden layers. Then, we explain the typical (non-linear) activation functions.
-
Chapter 08.04: Single Hidden Layer Networks for Multi-Class Classification
In this section, we discuss a neural network architectures for multi-class classification, softmax activation function as well as the Softmax loss.
-
Chapter 08.05: MLP: Multi-Layer Feedforward Neural Networks
Architectures of deep neural networks and deep neural networks as chained functions are the learning goal of this part.
-
Extra: Brief History
We overview history of DL development.
-
Extra: Basic Backpropagation 1
This section introduces forward and backward passes, chain rule, and the details of backprop in deep learning.