Industry
Dynamically Adaptable CMOS Winner-Take-All Neural Network
Iizuka, Kunihiko, Miyamoto, Masayuki, Matsui, Hirofumi
The major problem that has prevented practical application of analog neuro-LSIs has been poor accuracy due to fluctuating analog device characteristics inherent in each device as a result of manufacturing. This paper proposes a dynamic control architecture that allows analog silicon neural networks to compensate for the fluctuating device characteristics and adapt to a change in input DC level. We have applied this architecture to compensate for input offset voltages of an analog CMOS WTA (Winner-Take-AlI) chip that we have fabricated. Experimental data show the effectiveness of the architecture.
On-line Policy Improvement using Monte-Carlo Search
Tesauro, Gerald, Galperin, Gregory R.
Policy iteration is known to have rapid and robust convergence properties, and for Markov tasks with lookup-table state-space representations, it is guaranteed to convergence to the optimal policy. Online Policy Improvement using Monte-Carlo Search 1069 In typical uses of policy iteration, the policy improvement step is an extensive off-line procedure. For example, in dynamic programming, one performs a sweep through all states in the state space. Reinforcement learning provides another approach to policy improvement; recently, several authors have investigated using RL in conjunction with nonlinear function approximators to represent the value functions and/or policies (Tesauro, 1992; Crites and Barto, 1996; Zhang and Dietterich, 1996). These studies are based on following actual state-space trajectories rather than sweeps through the full state space, but are still too slow to compute improved policies in real time.
Probabilistic Interpretation of Population Codes
Zemel, Richard S., Dayan, Peter, Pouget, Alexandre
We present a theoretical framework for population codes which generalizes naturally to the important case where the population provides information about a whole probability distribution over an underlying quantity rather than just a single value. We use the framework to analyze two existing models, and to suggest and evaluate a third model for encoding such probability distributions.
A Micropower Analog VLSI HMM State Decoder for Wordspotting
Lazzaro, John, Wawrzynek, John, Lippmann, Richard P.
We describe the implementation of a hidden Markov model state decoding system, a component for a wordspotting speech recognition system. The key specification for this state decoder design is microwatt power dissipation; this requirement led to a continuoustime, analog circuit implementation. We characterize the operation of a 10-word (81 state) state decoder test chip.
Neural Network Models of Chemotaxis in the Nematode Caenorhabditis Elegans
Ferrรฉe, Thomas C., Marcotte, Ben A., Lockery, Shawn R.
We train recurrent networks to control chemotaxis in a computer model of the nematode C. elegans. The model presented is based closely on the body mechanics, behavioral analyses, neuroanatomy and neurophysiology of C. elegans, each imposing constraints relevant for information processing. Simulated worms moving autonomously in simulated chemical environments display a variety of chemotaxis strategies similar to those of biological worms. 1 INTRODUCTION The nematode C. elegans provides a unique opportunity to study the neuronal basis of neural computation in an animal capable of complex goal-oriented behaviors. The adult hermaphrodite is only 1 mm long, and has exactly 302 neurons and 95 muscle cells. The morphology of every cell and the location of most electrical and chemical synapses are known precisely (White et al., 1986), making C. elegans especially attractive for study.
Effective Training of a Neural Network Character Classifier for Word Recognition
Yaeger, Larry S., Lyon, Richard F., Webb, Brandyn J.
We have been conducting research on bottom-up classification techniques ba;ed on trainable artificial neural networks (ANNs), in combination with comprehensive but weakly-applied language models. To focus our work on a subproblem that is tractable enough to le.:'ld to usable products in a reasonable time, we have restricted the domain to hand-printing, so that strokes are clearly delineated by pen lifts. In the process of optimizing overall performance of the recognizer, we have discovered some useful techniques for architecting and training ANNs that must participate in a larger recognition process. Some of these techniques-especially the normalization of output error, frequency balanCing, and error emphal;is-suggest a common theme of significant value derived by reducing the effect of a priori biases in training data to better represent low frequency, low probability smnples, including second and third choice probabilities. There is mnple prior work in combining low-level classifiers with various search strategies to provide integrated segmentation and recognition for writing (Tappert et al 1990) and speech (Renals et aI1992). And there is a rich background in the use of ANNs a-; classifiers, including their use as a low-level, character classifier in a higher-level word recognition system (Bengio et aI1995).
Selective Integration: A Model for Disparity Estimation
Gray, Michael S., Pouget, Alexandre, Zemel, Richard S., Nowlan, Steven J., Sejnowski, Terrence J.
Local disparity information is often sparse and noisy, which creates two conflicting demands when estimating disparity in an image region: the need to spatially average to get an accurate estimate, and the problem of not averaging over discontinuities. We have developed a network model of disparity estimation based on disparityselective neurons, such as those found in the early stages of processing in visual cortex. The model can accurately estimate multiple disparities in a region, which may be caused by transparency or occlusion, in real images and random-dot stereograms. The use of a selection mechanism to selectively integrate reliable local disparity estimates results in superior performance compared to standard back-propagation and cross-correlation approaches. In addition, the representations learned with this selection mechanism are consistent with recent neurophysiological results of von der Heydt, Zhou, Friedman, and Poggio [8] for cells in cortical visual area V2. Combining multi-scale biologically-plausible image processing with the power of the mixture-of-experts learning algorithm represents a promising approach that yields both high performance and new insights into visual system function.
Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems
Singh, Satinder P., Bertsekas, Dimitri P.
In cellular telephone systems, an important problem is to dynamically allocate the communication resource (channels) so as to maximize service in a stochastic caller environment. This problem is naturally formulated as a dynamic programming problem and we use a reinforcement learning (RL) method to find dynamic channel allocation policies that are better than previous heuristic solutions. The policies obtained perform well for a broad variety of call traffic patterns.
Visual Cortex Circuitry and Orientation Tuning
Mundel, Trevor, Dimitrov, Alexander, Cowan, Jack D.
A simple mathematical model for the large-scale circuitry of primary visual cortex is introduced. It is shown that a basic cortical architecture of recurrent local excitation and lateral inhibition can account quantitatively for such properties as orientation tuning. The model can also account for such local effects as cross-orientation suppression. It is also shown that nonlocal state-dependent coupling between similar orientation patches, when added to the model, can satisfactorily reproduce such effects as non-local iso--orientation suppression, and non-local crossorientation enhancement. Following this an account is given of perceptual phenomena involving object segmentation, such as "popout", and the direct and indirect tilt illusions.
Efficient Nonlinear Control with Actor-Tutor Architecture
A new reinforcement learning architecture for nonlinear control is proposed. A direct feedback controller, or the actor, is trained by a value-gradient based controller, or the tutor. This architecture enables both efficient use of the value function and simple computation for real-time implementation. Good performance was verified in multidimensional nonlinear control tasks using Gaussian softmax networks.