DescriptionThis course is designed to introduce students to the concepts of machine learning (ML) and artificial intelligence (AI) in a hands-on manner. The course will begin with a quick introduction to Python and the theoretical foundations of basic machine learning and artificial intelligence concepts. Learning Objectives: Students will start with a simple linear regression example where they will derive and implement the gradient descent for a curve-fitting problem and understand the concepts of the loss function, regularization techniques, and bias-variance trade-off. The students will then be introduced to stochastic gradient 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 to train the neural network. Following this, the students will be introduced to Convolutional Neural Networks and will implement MNIST classification with CNNs. The student will understand how Pytorch and TensorFlow handle the forward and backward pass during training.The students will implement state-of-the-art networks for saliency detection, semantic segmentation, etc. As exercises for the course, the students will try to solve the practical problems of machine learning and artificial intelligence from diverse domains. You need to attend following sessions to get the credits: 1/4: 17 Jan 2021 3:30 - 5:00 PM AT 2/4: 18 Jan 2021 3:30 - 5:00 PM AT 3/4: 19 Jan 2021 3:30 - 5:00 PM AT 4/4: 20 Jan 2021 3:30 - 5:00 PM AT
Dr. Naeemullah Khan received his masters and Ph.D. degrees from Kaust in 2014 and 2018 respectively, in Electrical Engineering. Since 2018 he has been part of the Torr vision group (TVG) at the department of engineering, the University of Oxford. The primary focus of his research is the theoretical evaluation of deep networks. He has also been involved in several courses and summer schools on machine learning at artificial intelligence at the University of Oxford.
No resources found.
No links found.