About Course
This Advanced Deep Learning and Reinforcement Learning course, taught originally at UCL and recorded for online access, has two interleaved parts that converge towards the end of the course.
One part is on Advanced Deep Learning with deep neural networks, the other part is about prediction and control using reinforcement learning. The two strands come together when we discuss deep reinforcement learning, where deep neural networks are trained as function approximators in a reinforcement learning setting.
The deep learning stream of the course will cover a short introduction to neural networks and supervised learning with TensorFlow, followed by lectures on convolutional neural networks, recurrent neural networks, end-to-end and energy-based learning, optimization methods, unsupervised learning as well as attention and memory. Possible application areas to be discussed include object recognition and natural language processing.
The reinforcement learning stream will cover Markov decision processes, planning by dynamic programming, model-free prediction and control, value function approximation, policy gradient methods, integration of learning and planning, and the exploration/exploitation dilemma. Possible applications to be discussed include learning to play classic board games as well as video games.
Join to Advanced Deep Learning and Reinforcement Learning course>
Course Content
Advanced Deep Learning & Reinforcement Learning
-
Deep Learning 1: Introduction to Machine Learning Based AI
00:00 -
Deep Learning 8: Unsupervised learning and generative models
00:00 -
Reinforcement Learning 9: A Brief Tour of Deep RL Agents
00:00 -
Deep Learning 7. Attention and Memory in Deep Learning
00:00 -
Reinforcement Learning 8: Advanced Topics in Deep RL
00:00 -
Deep Learning 6: Deep Learning for NLP
00:00 -
Reinforcement Learning 7: Planning and Models
00:00 -
Deep Learning 5: Optimization for Machine Learning
00:00 -
Reinforcement Learning 6: Policy Gradients and Actor Critics
00:00 -
Reinforcement Learning 5: Function Approximation and Deep Reinforcement Learning
00:00 -
Deep Learning 4: Beyond Image Recognition, End-to-End Learning, Embeddings
00:00 -
Reinforcement Learning 4: Model-Free Prediction and Control
00:00 -
Reinforcement Learning 3: Markov Decision Processes and Dynamic Programming
00:00 -
Reinforcement Learning 2: Exploration and Exploitation
00:00 -
Reinforcement Learning 1: Introduction to Reinforcement Learning
00:00 -
Deep Learning 3: Neural Networks Foundations
00:00 -
Deep Learning 2: Introduction to TensorFlow
00:00 -
Reinforcement Learning 10: Classic Games Case Study
00:00
Student Ratings & Reviews
