This talk aims to provide a broad introduction to the theory and approaches for learning under uncertainty. The general goal of these approaches is to build an agent that maximizes rewards for a particular behaviour as the agent interacts with a random Environment in a feedback loop. The agent updates its policy or strategy for making decisions in the face of uncertainty by the responses the agent receives from the Environment. This talk will show examples of training agents in different Environments using the TensorFlow Agents library.

Speaker: Ekaba Bisong - Principal Consultant & Research Scientist, SiliconBlast

Ekaba is involved in AI and ML Research at SiliconBlast. Ekaba has proven expertise in designing and implementing enterprise data engineering architectures and advanced analytics products. He has worked with AI development tools such as Tensorflow, Keras and PyTorch. He is also experienced in Cloud Data Engineering and Software Development.

Ekaba’s work has involved consulting for top companies within North America, where he has led teams of Data Engineers and Scientists to deliver enterprise AI, ML and advanced analytics products. His experience spans various verticals from banking to mining, oil and gas, sports, media and medicine. In addition, Ekaba maintains a relationship with the Intelligent Systems Labs at Carleton University with a research focus on Learning Systems (encompassing learning automata and reinforcement learning), Machine Learning, and Deep Learning.

Ekaba is a Google Developer Expert in Machine Learning and author of the book “Building Machine Learning and Deep Learning Models on Google Cloud Platform” with Apress (Springer Nature) Publishers.