Friedman's combination rule is quite intuitive: assign to the class that wins the most pairwise comparisons.

We study the storage capacity of a fully-connected committee machine witha large number K of hidden nodes. The storage capacity is obtained by analyzing the geometrical structure of the weight space related to the internal representation.

Motivated by the findings of modular structure in the association cortex, we study a multi-modular model of associative memory that can successfully store memory patterns with different levels of activity. Weshow that the segregation of synaptic conductances into intra-modular linear and inter-modular nonlinear ones considerably enhances the network's memory retrieval performance. Compared with the conventional, single-module associative memory network, the multi-modular network has two main advantages: It is less susceptible todamage to columnar input, and its response is consistent with the cognitive data pertaining to category specific impairment. 1 Introduction Cortical modules were observed in the somatosensory and visual cortices a few decades ago. These modules differ in their structure and functioning but are likely to be an elementary unit of processing in the mammalian cortex. Within each module the neurons are interconnected.

The hardware implementation of neural networks is crucial in order to realize the real-time operation of neural functions such as spatiotemporal filtering, learning and constraint processings. Since the mid eighties, many VLSI chips and systems have been reported in the literature, e.g.

A Lyapunov function for excitatory-inhibitory networks is constructed. The construction assumes symmetric interactions within excitatory and inhibitory populations of neurons, and antisymmetric interactions between populations.The Lyapunov function yields sufficient conditions for the global asymptotic stability of fixed points. If these conditions are violated, limit cycles may be stable. The relations of the Lyapunov function to optimization theory and classical mechanics are revealed by minimax and dissipative Hamiltonian forms of the network dynamics. The dynamics of a neural network with symmetric interactions provably converges to fixed points under very general assumptions[l, 2].

Advanced Technology R&D Center Mitsubishi Electric Corporation Amagasaki, Hyogo 661-0001, Japan Abstract A learning system composed of linear control modules, reinforcement learningmodules and selection modules (a hybrid reinforcement learning system) is proposed for the fast learning of real-world control problems. The selection modules choose one appropriate control module dependent on the state. It learned the control on a sloped floor more quickly than the usual reinforcement learningbecause it did not need to learn the control on a flat floor, where the linear control module can control the robot. When it was trained by a 2-step learning (during the first learning step, the selection module was trained by a training procedure controlled onlyby the linear controller), it learned the control more quickly. The average number of trials (about 50) is so small that the learning system is applicable to real robot control. 1 Introduction Reinforcement learning has the ability to solve general control problems because it learns behavior through trial-and-error interactions with a dynamic environment.

R Pmin/Pmax is the ratio of the minimum and maximum state-action occupation frequencies.

The Natural abstract actions are to move from room to room. 1 Reinforcement Learning (MDP) Framework In reinforcement learning, a learning agent interacts with an environment at some discrete, lowest-level time scale t 0,1,2, ... On each time step, the agent perceives the state of the environment, St, and on that basis chooses a primitive action, at.

We present a new approach to reinforcement learning in which the policies consideredby the learning process are constrained by hierarchies of partially specified machines. This allows for the use of prior knowledge to reduce the search space and provides a framework in which knowledge can be transferred across problems and in which component solutions can be recombined to solve larger and more complicated problems. Our approach can be seen as providing a link between reinforcement learning and"behavior-based" or "teleo-reactive" approaches to control. We present provably convergent algorithms for problem-solving and learning withhierarchical machines and demonstrate their effectiveness on a problem with several thousand states.

Weconsider a deterministic system with continuous state and time with infinite horizon discounted cost functional.