Neuromorphic engineers work to improve the performance of artificial systems through the development of chips and systems that process information collectively using primarily analog circuits. This book presents the central concepts required for the creative and successful design of analog VLSI circuits. The discussion is weighted toward novel circuits that emulate natural signal processing. Unlike most circuits in commercial or industrial applications, these circuits operate mainly in the subthreshold or weak inversion region.
The Neural Simulation Language (NSL), developed by Alfredo Weitzenfeld, Michael Arbib, and Amanda Alexander, provides a simulation environment for modular brain modeling. NSL is an object-oriented language offering object-oriented protocols applicable to all levels of neural simulation. One of NSL's main strengths is that it allows for realistic modeling of the anatomy of macroscopic brain structures.
Neurophysiological, neuroanatomical, and brain imaging studies have helped to shed light on how the brain transforms raw sensory information into a form that is useful for goal-directed behavior. A fundamental question that is seldom addressed by these studies, however, is why the brain uses the types of representations it does and what evolutionary advantage, if any, these representations confer. It is difficult to address such questions directly via animal experiments.
Graphical models use graphs to represent and manipulate joint probability distributions. They have their roots in artificial intelligence, statistics, and neural networks. The clean mathematical formalism of the graphical models framework makes it possible to understand a wide variety of network-based approaches to computation, and in particular to understand many neural network algorithms and architectures as instances of a broader probabilistic methodology.
This book provides an overview of self-organizing map formation, including recent developments. Self-organizing maps form a branch of unsupervised learning, which is the study of what can be determined about the statistical properties of input data without explicit feedback from a teacher. The articles are drawn from the journal Neural Computation.
The annual conference on Neural Information Processing Systems (NIPS) is the flagship conference on neural computation. The conference is interdisciplinary, with contributions in algorithms, learning theory, cognitive science, neuroscience, vision, speech and signal processing, reinforcement learning and control, implementations, and diverse applications. Only about 30 percent of the papers submitted are accepted for presentation at NIPS, so the quality is exceptionally high. These proceedings contain all of the papers that were presented at the 2000 conference.
The goal of computational cognitive neuroscience is to understand how the brain embodies the mind by using biologically based computational models comprising networks of neuronlike units. This text, based on a course taught by Randall O'Reilly and Yuko Munakata over the past several years, provides an in-depth introduction to the main ideas in the field. The neural units in the simulations use equations based directly on the ion channels that govern the behavior of real neurons, and the neural networks incorporate anatomical and physiological properties of the neocortex.
The annual conference on Neural Information Processing System (NIPS) is the flagship conference on neural computation. It draws preeminent academic researchers from around the world and is widely considered to be a showcase conference for new developments in network algorithms and architectures. The broad range of interdisciplinary research areas represented includes computer science, neuroscience, statistics, physics, cognitive science, and many branches of engineering, including signal processing and control theory.
Neurocomputing methods are loosely based on a model of the brain as a network of simple interconnected processing elements corresponding to neurons. These methods derive their power from the collective processing of artificial neurons, the chief advantage being that such systems can learn and adapt to a changing environment. In knowledge-based neurocomputing, the emphasis is on the use and representation of knowledge about an application. Explicit modeling of the knowledge represented by such a system remains a major research topic.
Our perception of the world is driven by input from the sensory nerves. This input arrives encoded as sequences of identical spikes. Much of neural computation involves processing these spike trains. What does it mean to say that a certain set of spikes is the right answer to a computational problem? In what sense does a spike train convey information about the sensory world? Spikes begins by providing precise formulations of these and related questions about the representation of sensory signals in neural spike trains.