In this paper we revisit the classical neuroscience paradigm of Hebbian learning. We find that a necessary requirement for effective associative memory learning is that the efficacies of the incoming synapses should be uncorrelated. This is difficult to achieve in a robust manner by Hebbian synaptic learning, since it depends on network level information. Effective learning can yet be achieved ...

Three challenges to the sufficiency of the associative account for explaining the development of mirror mechanisms are discussed: Genetic predispositions interact with associative learning, infants show predispositions to imitate human as opposed to nonhuman actions, and early and later learning involve different mechanisms. Legitimate objections to an extreme nativist account are raised, but t...

In this paper, we propose a Hetero Chaotic Associative Memory for Successive Learning (HCAMSL) with give up function. The proposed model is based on a Chaotic Associative Memory for Successive Memory (CAMSL). In the proposed HCAMSL, the learning process and the recall process are not divided. When an unstored pattern is given to the network, the HCAMSL can learn the pattern successively.

A computational model of sequence learning is described that is based on pairwise associations and generalization. Simulations by the model predicted that rats should learn a long monotonic pattern of food quantities better than a nonmonotonic pattern, as predicted by rule-learning theory, and that they should learn a short nonmonotonic pattern with highly discriminable elements better than 1 w...

In this paper, we present FPGA recurrent neural network systems with learning capability using the simultaneous perturbation learning rule. In the neural network systems, outputs and internal values are represented by pulse train. That is, analog recurrent neural networks with pulse frequency representation are considered. The pulse density representation and the simultaneous perturbation enabl...

Recently, neural networks are drawing much attention as a method to realize flexible information processing. Neural networks consider neuron groups of the brain in the creature, and imitate these neurons technologically. Neural networks have some features, especially one of the important features is that the networks can learn to acquire the ability of information processing. In the filed of ne...

In this position paper we propose to enhance learning algorithms, reinforcement learning in particular, for agents and for multi-agent systems, with the introduction of concepts and mechanisms borrowed from associative learning theory. It is argued that existing algorithms are limited in that they adopt a very restricted view of what “learning” is, partly due to the constraints imposed by the M...

By using neurocognitive evidence on mirror neuron system concepts the MirrorBot project has developed neural models for intelligent robot behaviour. These models employ diverse learning approaches such as reinforcement learning, self-organisation and associative learning to perform cognitive robotic operations such as language grounding in actions, object recognition, localisation and docking. ...

In this paper we propose new paradigm combining concepts “programming”, “learning” and “context” for usage in development of control system of mobile robots and other intelligent agents in smart environment. And we suggest architecture of robot’s control system based on context and learning with natural language dialog. The core of this architecture is associative memory for cross-modal learnin...

Appetitive learning of food-predicting stimuli, an essential part of foraging behavior in honeybees, follows the rules of associative learning. In the learning of odors as reward-predicting stimuli, an individual neuron, one of a small group of large ascending neurons that serve principal brain neuropiles, mediates the reward and has experience-dependent response properties. This implies that t...