David Barber Follow


David is the Director of the UCL Centre for Artificial Intelligence


Posts by David Barber

AI Coworkers

We argue for a more interactive approach in which AI systems function more like coworkers. For them to be effective in this role, they need to have reasonable estimates of confidence ...

In General, Jun 01, 2020

Training Models that have Zero Likelihood

How can we train generative models when we cannot calculate a gradient likelihood?

In Optimization, Dec 21, 2019

Learning From Scratch by Thinking Fast and Slow with Deep Learning and Tree Search

According to dual process theory human reasoning consists of two different kinds of thinking.System 1 is a fast, unconscious and automatic mode of thought, also known as intuition. Sy...

In Reinforcement Learning, Nov 07, 2017

Some modest insights into the error surface of Neural Nets

Did you know that feedforward Neural Nets (with piecewise linear transfer functions) have no smooth local maxima?

In Optimization, Jul 30, 2017

Evolutionary Optimization as a Variational Method

How popular evolutionary style optimisation methods can be viewed as optimisation of a rigorous bound.

In Optimization, Apr 03, 2017

Training with a large number of classes

In machine learning we often face the issue of a very large number of classes in a classification problem. This causes a bottleneck in the computation. There’s though a simple and eff...

In Classification, Mar 15, 2017