Lecture Notes: Neural Network Architectures
This is an incremental educational resource for students or researchers seeking a foundational mathematical perspective on neural networks.
The lecture notes tackle the problem of understanding neural network architectures by providing a mathematical overview, framing machine learning with neural networks as an optimization problem and covering key architectures such as Feedforward, Convolutional, ResNet, and Recurrent Neural Networks.
These lecture notes provide an overview of Neural Network architectures from a mathematical point of view. Especially, Machine Learning with Neural Networks is seen as an optimization problem. Covered are an introduction to Neural Networks and the following architectures: Feedforward Neural Network, Convolutional Neural Network, ResNet, and Recurrent Neural Network.