Towards a generalized theory comprising digital, neuromorphic and unconventional computing

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

The accelerating race of digital computing technologies seems to be steering towards impasses—technological, economical and environmental—a condition that has spurred research efforts in alternative, ‘neuromorphic’ (brain-like) computing technologies. Furthermore, for decades, the idea of exploiting nonlinear physical phenomena ‘directly’ for non-digital computing has been explored under names like ‘unconventional computing’, ‘natural computing’, ‘physical computing’, or ‘in-materio computing’. In this article I investigate coordinates and conditions for a generalized concept of ‘computing’ which comprises digital, neuromorphic, unconventional and possible future ‘computing’ paradigms. The main contribution of this paper is an in-depth inspection of existing formal conceptualizations of ‘computing’ in discrete-symbolic, probabilistic and dynamical-systems oriented views. It turns out that different choices of background mathematics lead to decisively different understandings of what ‘computing’ is. However, across this diversity a unifying coordinate system for theorizing about ‘computing’ can be distilled.

Related collections

Most cited references 131

Record: found
Abstract: found
Article: not found

Optimization by simulated annealing.

S. Kirkpatrick, C D Gelatt, M. P. Vecchi (1983)

There is a deep and useful connection between statistical mechanics (the behavior of systems with many degrees of freedom in thermal equilibrium at a finite temperature) and multivariate or combinatorial optimization (finding the minimum of a given function depending on many parameters). A detailed analogy with annealing in solids provides a framework for optimization of the properties of very large and complex systems. This connection to statistical mechanics exposes new information and provides an unfamiliar perspective on traditional optimization problems and methods.

0 comments Cited 1591 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Reducing the dimensionality of data with neural networks.

G E Hinton, R R Salakhutdinov (2006)

High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuning the weights in such "autoencoder" networks, but this works well only if the initial weights are close to a good solution. We describe an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.

0 comments Cited 1537 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Mastering the game of Go with deep neural networks and tree search.

David Silver, Aja Huang, Chris J Maddison … (2016)

The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses 'value networks' to evaluate board positions and 'policy networks' to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of state-of-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.