The INI has a new website!

This is a legacy webpage. Please visit the new site to ensure you are seeing up to date information.

Isaac Newton Institute for Mathematical Sciences

Neural Networks and Machine Learning

July - December 1997

Organisers: C M Bishop (Aston), D Haussler (UCSC), G E Hinton (Toronto), M Niranjan (Cambridge), L G Valiant (Harvard)

Bayesian Methods

14 Dec--20 Dec 1997

Isaac Newton Institute, Cambridge, U.K.

Monday 15 December

10.00-11.00 M Niranjan (Cambridge)
Bayesian methods in nonlinear signal processing

11.00-11.30 Coffee

11.30-12.30 C Bishop (Microsoft Research)
Ensemble learning

12.30-14.00 Lunch

14.00-15.00 C Rasmussen (Toronto)
Gaussian processes

15.00-15.30 Tea

15.30-18.00 Poster Session

17.00-18.00 Wine Reception

Tuesday 16 December

10.00-11.00 CK Williams (Aston)
Gaussian processes

11.00-11.30 Coffee

11.30-12.30 S Luttrell (DERA)
Optimal posterior probabilities in soft-encoder networks

12.30-14.00 Lunch

14.00-15.00 J Shawe-Taylor (Royal Hollaway)
A PAC analysis of a Bayesian estimator

15.00-15.30 Tea

15.30-16.30 D Haussler (UCSC)
From bayes to worst case

16.45-17.45 M Opper (Aston)
From bayes to worst case

Wednesday 17 December

10.00-11.00 S Russell (Berkeley)
Probabilistic models of comples processes

11.00-11.30 Coffee

11.30-12.30 A Gelman (Columbia)
Checking the fit of complex models

12.30-14.00 Lunch

14.00-15.00 P Green (Bristol)
Variable dimension MCMC: change-points and mixtures

15.00-15.30 Tea

15.30-16.30 T Richardson (Washington)
Graphical models with interpretable structure

16.45-17.45 R Rohwer (HNC)
Bayesian theory of RAMnets

Thursday 18 December

10.00-11.00 S-I Amari (Tokyo)
Independent component analysis

11.00-11.30 Coffee

11.30-12.30 T Sejnowski (Salk Inst.)
Independent component analysis

12.30-14.00 Lunch

14.00-15.00 D MacKay (Cambridge)
Independent component analysis

15.00-15.30 Tea

15.30-16.30 J Karhunen (Helsinki)
Neural independent component analysis and blind source separation - some new results

16.45-17.45 J-F Cardoso (ENST)
Likelihood approximations for ICA and the use of prior information

19.00- . Conference Dinner

Friday 19 December

10.00-11.00 Y Singer (AT&T)
Bayesian methods in stock markets

11.00-11.30 Coffee

11.30-12.30 W Fitzgerald (Cambridge)
Signal processing

12.30-14.00 Lunch

14.00-15.00 D Saad (Aston)
Evidenc, MAP and the generalization error - a statistical mechanical perspective

15.00-15.30 Tea

15.30-16.30 G Hinton (Toronto)

16.45-17.45 M Feder (Technion)

This workshop will form a component of the Newton Institute programme on Neural Networks and Machine Learning, organised by C M Bishop, D Haussler, G E Hinton, M Niranjan and L G Valiant.

Copyright © Isaac Newton Institute