Author name cluster

Jacques Vidal

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

NeurIPS Conference 1990 Conference Paper

Adaptive Range Coding

Bruce Rosen
James Goodwin
Jacques Vidal

these to neuron-like processing elements. "neurons" This paper examines a class of neuron based that rely on learning systems for dynamic control adaptive range coding of sensor inputs. Sensors are assumed to provide binary coded range vectors that coarsely describe the system state. These vectors are Output input decisions generated by turn the system state, subsequently producing new affect inputs. the intervals and environment are evaluated. The neural weights as well as the ran g e b 0 u n dar i e s determining the output decisions are then altered with future Preliminary reinforcement from the promise of adapting "neural experiments show receptive learning dynamical control. The observed performance with this method exceeds that of earlier approaches. the goal of maximizing the environment.

PDF Details

NeurIPS Conference 1987 Conference Paper

LEARNING BY STATE RECURRENCE DETECTION

Bruce Rosen
James Goodwin
Jacques Vidal

This research investigates a new technique for unsupervised learning of nonlinear control problems. The approach is applied both to Michie and Chambers BOXES algorithm and to Barto, Sutton and Anderson's extension, the ASE/ACE system, and has significantly improved the convergence rate of stochastically based learning automata. Recurrence learning is a new nonlinear reward-penalty algorithm. It exploits information found during learning trials to reinforce decisions resulting in the recurrence of nonfailing states. Recurrence learning applies positive reinforcement during the exploration of the search space, whereas in the BOXES or ASE algorithms, only negative weight reinforcement is applied, and then only on failure. Simulation results show that the added information from recurrence learning increases the learning rate. Our empirical results show that recurrence learning is faster than both basic failure driven learning and failure prediction methods. Although recurrence learning has only been tested in failure driven experiments, there are goal directed learning applications where detection of recurring oscillations may provide useful information that reduces the learning time by applying negative, instead of positive reinforcement. Detection of cycles provides a heuristic to improve the balance between evidence gathering and goal directed search.

PDF Details

NeurIPS Conference 1987 Conference Paper

Synchronization in Neural Nets

Jacques Vidal
John Haggerty

The paper presents an artificial neural network concept (the Synchronizable Oscillator Networks) where the instants of individual firings in the form of point processes constitute the only form of information transmitted between joining neurons. This type of communication contrasts with that which is assumed in most other models which typically are continuous or discrete value-passing networks. Limiting the messages received by each processing unit to time markers that signal the firing of other units presents significant implemen tation advantages. In our model, neurons fire spontaneously and regularly in the absence of perturbation. When interaction is present, the scheduled firings are advanced or delayed by the firing of neighboring neurons. Networks of such neurons become global oscillators which exhibit multiple synchronizing attractors. From arbitrary initial states, energy minimization learning procedures can make the network converge to oscillatory modes that satisfy multi-dimensional constraints Such networks can directly represent routing and scheduling problems that conSist of ordering sequences of events.

PDF Details