An Introduction to AI Unit 3: Evaluating Neural Networks
This unit will explore methods of evaluating neural networks and AI systems to see if they are working well. We will discuss two key techniques: backpropagation and gradient descent. This unit provides an introduction and intuitive explanation rather than a thorough mathematical exposition. In practice, AI systems are implemented via computer programs with a set of pre-written libraries. We will also look at some real data in the area of handwriting recognition to see how data is ingested.
All prices shown are exclusive of VAT which will be added at checkout
Dr. Ronjon Nag
Dr. Ronjon Nag has an Engineering PhD (Cambridge), an SM in Management Science (MIT) and a B.Sc. in Electrical Engineering (Birmingham). He is president of the R42 Institute and he became a Stanford University Interdisciplinary Distinguished Careers Institute Fellow at the Center for Study for Language and Information in 2016. He works on the Boundaries of Humanity Project looking at intelligence in humans, animals and machines in the age of biotechnology and artificial intelligence. He teaches at Stanford Medical School. He is an active Advisor and Board Member to some 70 AI and Biotech companies. He has also been awarded the IET Mountbatten Medal for contributions to the mobile phone industry.
• Understand how to find the parameters of neural networks.
• Understand backpropagation and gradient descent.
• Understand how to train neural networks on an online system.
• Have explored some real-world applications of neural networks.
• Understand how to evaluate neural networks and AI systems.
• Understand the difference between overfitting and underfitting.