Neural networks : the official journal of the International Neural Network Society
Apr 27, 2017
The purpose of supervised learning with temporal encoding for spiking neurons is to make the neurons emit a specific spike train encoded by precise firing times of spikes. The gradient-descent-based (GDB) learning methods are widely used and verified...
Humans regularly perform new learning without losing memory for previous information, but neural network models suffer from the phenomenon of catastrophic forgetting in which new learning impairs prior function. A recent article presents an algorithm...
Towards practical realization of brain-inspired computing in a scalable physical system, we investigate a network of coupled micromechanical oscillators. We numerically simulate this array of all-to-all coupled nonlinear oscillators in the presence o...
Proceedings of the National Academy of Sciences of the United States of America
Mar 14, 2017
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Until now neural networks have not been capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature ...
Proceedings of the National Academy of Sciences of the United States of America
Mar 13, 2017
Social behavior is often shaped by the rich storehouse of biographical information that we hold for other people. In our daily life, we rapidly and flexibly retrieve a host of biographical details about individuals in our social network, which often ...
Journal of psychopharmacology (Oxford, England)
Dec 14, 2016
The present study compared the cognitive and mood effects of two commercially available products, Red Bull energy drink 250 mL and Red Bull Sugarfree energy drink 250 mL, together with a matching placebo 250 mL. Twenty-four healthy young volunteers t...
Neural networks : the official journal of the International Neural Network Society
Dec 7, 2016
Electrophysiological studies in animals may provide a great insight into developing brain-like models of spatial cognition for robots. These studies suggest that the spatial ability of animals requires proper functioning of the hippocampus and the en...
This paper is intended to propose a computational model for memory from the view of information processing. The model, called simplified memory information retrieval network (SMIRN), is a bi-modular hierarchical functional memory network by abstracti...
Computational intelligence and neuroscience
Nov 3, 2016
Identifying the hidden state is important for solving problems with hidden state. We prove any deterministic partially observable Markov decision processes (POMDP) can be represented by a minimal, looping hidden state transition model and propose a h...
Computational intelligence and neuroscience
Oct 19, 2016
We investigate a class of memristor-based shunting inhibitory cellular neural networks with leakage delays. By applying a new Lyapunov function method, we prove that the neural network which has a unique almost periodic solution is globally exponenti...