This is a live, real-time online course with teaching delivered Monday to Friday 9 am – 3 pm BST (UK) time with 3 hours of lectures and 2 hours of assignments per day.

Course outline:
The course will begin with a quick introduction of Python and the theoretical foundations of basic concepts in machine learning and artificial intelligence. Students will start with a simple linear regression example where they will derive and implement the gradient descent for a curve fitting problem and try to understand the concepts of loss function, regularization techniques, and bias-variance trade-off. The students will then be introduced to stochastic gradients descent and will implement stochastic gradient descent for regression using TensorFlow and Pytorch.
The students will design simple neural networks for MNIST classification and implement the full forward and backward pass for the training of the neural network. Following which the students will be introduced to Convolutional Neural Networks and will implement MNIST classification with CNNs. The student will understand how Pytorch and TensorFlow handles the forward and backward pass during training.
As exercises for the course, the students will try to solve small scale practical problems of machine learning and artificial intelligence from diverse domains.
To benefit from the course students need a basic knowledge of calculus and linear algebra. No prior knowledge of machine learning and artificial intelligence is essential.