University of Cambridge > Talks.cam > Machine Learning @ CUED > Training and Understanding Deep Neural Networks for Robotics, Design, and Perception

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Training and Understanding Deep Neural Networks for Robotics, Design, and Perception

Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani .

Artificial Neural Networks (ANNs) form a powerful class of models with both theoretical and practical advantages. Networks with more than one hidden layer (deep neural networks) compute multiple functions on later layers that share the use of intermediate results computed on earlier layers. This compositional, hierarchical structure provides a strong bias, or regularization, toward solutions that seem to work well on a large variety of real-world problems.

In this talk I will begin by showing a few examples of how this general compositional bias can excel at such diverse tasks as designing robot gaits and 3D objects. I will then discuss a few simple experiments that shed light on the inner workings of neural nets trained to classify images. The first study examines the computation performed by the entire set of neurons on a layer in a network, and subsequent work illuminates the computation performed by individual units, and finally the computation performed by the network as a whole. The experiments taken together reveal some surprising behaviors of large networks and lead to a greater understanding and intuition for the computation performed by deep neural nets.

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Lecture Theatre LAB002, East Road, Anglia Ruskin University, Cambridge B2.002, Ray Dolby Centre, Cavendish Laboratory Lecture Theatre, Medical Research Council Cognition and Brain Sciences Unit

Other talks

 Life, death, and the discovery of PDAR: the Pol II Degradation-dependent Apoptotic Response  Good and Evil Plasma Cells: Guardians & Saboteurs of Immunity Evolutionary constraints shape the evolution of mammalian tooth classes Quantum graphs with a time asymmetry: spectral optimization and spectral statistics Loke CTR Seminar Series - Vincent Pasque Afternoon Break
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity