University of Cambridge > Talks.cam > Machine Learning @ CUED > Direction-Only Optimisation for Neural Networks

  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

ℹī¸ Information

Direction-Only Optimisation for Neural Networks

Download to your calendar using vCal

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

Short talk

Optimisation routines form an important part of many learning algorithms for neural networks, and variants of the stochastic gradient descent algorithm are popular choices in practice. In this talk I will briefly present the results of a small research project into the effectiveness of a direction-only optimisation technique in neural network learning, carried out as part of my initial year at the Cambridge Centre for Analysis DTC .

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

Potter Room / https://cam-ac-uk.zoom.us/j/87235967698 Average on weekdays: 8814.09259259 kWh Chemical Engineering and Biotechnology occasional seminars

Other talks

Talk TBC Grand Rounds - Equine Title to be confirmed Coming soon Title to be confirmed The elephant in the room: Machine Learning directly into physical models
 

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