Learn More
Modelling natural images with sparse coding (SC) has faced two main challenges: flexibly representing varying pixel intensities and realistically representing low-level image components. This paper proposes a novel multiple-cause generative model of low-level image statistics that generalizes the standard SC model in two crucial points: (1) it uses a(More)
We present a neural network that is capable of completing and correcting a spiking pattern given only a partial, noisy version. It operates in continuous time and represents information using the relative timing of individual spikes. The network is capable of correcting and recalling multiple patterns simultaneously. We analyze the network's performance in(More)
Sparse coding is a popular approach to model natural images but has faced two main challenges: modelling low-level image components (such as edge-like structures and their occlusions) and modelling varying pixel intensities. Traditionally, images are modelled as a sparse linear superposition of dictionary elements, where the probabilistic view of this(More)
We develop a variant of a Bloom filter that is robust to hardware failure and show how it can be used as an efficient associative memory. We define a measure of the information recall and show that our new associative memory is able to recall more than twice as much information as a Hopfield network. The extra efficiency of our associative memory is all the(More)
Using recently obtained ac conductivity data we have derived dc conductivity together with free electron density and electron momentum relaxation time in two-temperature warm dense gold with energy density up to 4.1 MJ/kg (0.8×10^{11}J/m^{3}). The derivation is based on a Drude interpretation of the dielectric function that takes into account contributions(More)
This thesis examines applying reinforcement learning to sailing. We give two conceptually different models of a simple sailing boat. Standard tabular reinforcement learning is shown to be ineffective in controlling these naturally continuous models. We examine a method [Smith, 2001b] which adaptively quantises both the state and action spaces and show that(More)
This paper seeks to reduce the pricing noise inherent in a normal market structure, by requiring more pricing information to be communicated. Rather than individual buy or sell orders, the specication of an investor's entire demand function is provided. The demand function species how many shares the investor would like to own for all possible prices. The(More)
Can cooperation be learnt through reinforcement learning? This is the central question we pose in this paper. To answer it first requires an examination of what constitutes reinforcement learning. We also examine some of the issues associated with the design of a reinforcement learning system; these include: the choice of an update rule, whether or not to(More)
  • 1