-
Introduction to Linear Regression - mathematics and application with Python
Linear regression is among the most widely used tools in machine learning. Linear models are linear simply because the outputs are modeled as linear combinations of input vectors. Hence, we want to learn a function $f$ that describes with as little error as possible, the linear relationship between inputs and...
-
The Recurrent Neural Network - Theory and Implementation of the Elman Network and LSTM
Learning objectives Understand the principles behind the creation of the recurrent neural network Obtain intuition about difficulties training RNNs, namely: vanishing/exploding gradients and long-term dependencies Obtain intuition about mechanics of backpropagation through time BPTT Develop a Long Short-Term memory implementation in Keras Learn about the uses and limitations of RNNs...
-
The Convolutional Neural Network - Theory and Implementation of LeNet-5 and AlexNet
Learning objectives Understand the principles behind the creation of the convolutional network Gain an intuitive understanding of the convolution (feature map) and pooling (subsampling) operations Develop a basic code implementation of the LeNet-5 and AlexNet networks in Python Identify the similarities and differences between human vision and convolutional networks Historical...