This is an exciting course on deep learning & neural networks with major focus on both theory, mathematics behind and implementation in Python and Keras. The course starts by describing perceptron, the smallest unit of the neural network - its working, mathematics and implementation. Later we dive into deep forward networks where you learn how to build multi layer perceptrons(MLP's or feed forward networks) that can solve complex real life problems by learning complex functions such as back propagation. Special focus is given on understanding forward and backward propagation in matrix/vector form, and followed by efficient implementation of the same to build a deep forward network. You will learn to evaluate your model performance on various non-linear data-sets followed by two projects involving Fashion-MNIST and Pokemon Classifier! The next part of the course covers convolution neural networks, various classification backbones such as Alexnet, VGG, , Mobilenet in great detail followed by various Natural Language Processing topics such Word Embeddings, Recurrent Neural Networks. The course concludes with two capstone projects such Image Captioning & Music Generation.

A Comparison with our Similar Offerings