Deep Learning Course
Pre-requisites for the course : Some programming knowledge required
Basic Python programming
Some knowledge about ML algorithms but not necessary. We will teach you the rest.
Date: Course commences from the third week of February
1. Introduction to Deep Learning
Be able to explain the major trends driving the rise of deep learning, and understand where and how it is applied today.
2. Neural Networks Basics
Learn to set up a machine learning problem with a neural network mindset.
Learn to use vectorization to speed up your models.
3. Shallow Neural Networks
Learn to build a neural network with one hidden layer, using forward propagation and backpropagation.
4. Deep Neural Networks
Understand the key computations underlying deep learning, use them to build and train deep neural networks, and apply it to computer vision.
5. Optimization Algorithms
We will be looking into the evolution of optimization algorithms and the state of the art algorithms like Adagrad being used today.
6. Hyperparameter tuning, Batch Normalization and Programming Frameworks
Hyper parameter tuning forms the heart of any Deep Learning or Machine learning project, hence we will be looking into techniques which will help us do that.
7. Convolutional Neural Network
This module will teach you how to build convolutional neural networks and apply it to image data. Thanks to deep learning, computer vision is working far better than just two years ago, and this is enabling numerous exciting applications ranging from safe autonomous driving, to accurate face recognition, to automatic reading of radiology images
8. Sequence Modelling
This module will teach you how to build models for natural language, audio, and other sequence data. Thanks to deep learning, sequence algorithms are working far better than just two years ago, and this is enabling numerous exciting applications in speech recognition, music synthesis, chatbots, machine translation, natural language understanding, and many others. We will be looking into Recurrent Neural Networks (RNNs), and commonly-used variants such as GRUs and LSTMs.