Optical learning in a smart spatial light modulator

A synaptic plane rendered by an array of smart pixels was described regarding its application as a complementary component for neural network implementation. The smart spatial light modulator featured auto-modification abilities. Thus, an optical system incorporating this device can show self-reliant optical learning. Furthermore, the optical system design, in the area of its optical interconnection scheme, is highly flexible since the independent weight-plane pixels eliminated the difficulty between weight update calculation and weight representation.

Reinforcement learning for parameter estimation in statistical spoken dialogue systems

Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estimate the parameters of a dialogue policy which selects the system's responses based on the inferred dialogue state. However, the inference of the dialogue state itself depends on a dialogue model which describes the expected behaviour of a user when interacting with the system. Ideally the parameters of this dialogue model should be also optimised to maximise the expected cumulative reward. This article presents two novel reinforcement algorithms for learning the parameters of a dialogue model. First, the Natural Belief Critic algorithm is designed to optimise the model parameters while the policy is kept fixed. This algorithm is suitable, for example, in systems using a handcrafted policy, perhaps prescribed by other design considerations. Second, the Natural Actor and Belief Critic algorithm jointly optimises both the model and the policy parameters. The algorithms are evaluated on a statistical dialogue system modelled as a Partially Observable Markov Decision Process in a tourist information domain. The evaluation is performed with a user simulator and with real users. The experiments indicate that model parameters estimated to maximise the expected reward function provide improved performance compared to the baseline handcrafted parameters. © 2011 Elsevier Ltd. All rights reserved.

User responses to the learning demands of consumer products

Designers are typically male, under 35 years old and unimpaired. Users can be of any age and currently over 15% will have some form of impairment. As a result a vast array of consumer products suit youthful males and in many cases exclude other demographics (e.g. Keates and Clarkson, 2004). In studying the way a range of users learn how to use new products, key cognitive difficulties are revealed and linked back to the areas of the product causing the problems. The trials were structured so each user had to complete a specific set of tasks and were consistent across the user spectrum. The tasks set aimed to represent both everyday usage and less familiar functions. Whilst the knowledge gained could provide designers with valuable guidelines for the specific products examined, a more general abstraction provides knowledge of the pitfalls to avoid in the design of other product families.