Search Results

Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning. However, reinforcement learning (RL) algorithms struggle in POMDP environments because the state of the system, ...

The plasticity property of biological neural networks allows them to perform learning and optimize their behavior by changing their configuration. Inspired by biology, plasticity can be modeled in artificial neural networks by using Hebbian learning ...

Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in spiking neural ...

This paper contributes a computational model for developing a Post-Traumatic Stress Disorder (PTSD), based on insights from the neurological literature. A number of simulations are presented that show how under specific circumstances the model develops ...

The series of Where-What Networks (WWNs) is a brain-inspired developmental model that simulates the dorsal (where) stream and the ventral (what) stream that converge to the motor area in the frontal cortex. Since developmental learning is always ...

Autoencoders play a fundamental role in unsupervised learning and in deep architectures for transfer learning and other tasks. In spite of their fundamental role, only linear autoencoders over the real numbers have been solved analytically. Here we ...

Spiking Neuron Networks (SNNs) overcome the computational power of neural networks made of thresholds or sigmoidal units. Indeed, SNNs add a new dimension, the temporal axis, to the representation capacity and the processing abilities of neural ...

With the overwhelming development of network to large-scale, heterogeneity and high-speed, policy-based management becomes a promising solution, but its static policy configurations can not accord with the target of self-management. Inspired by ...

As an alternative to classical representations in machine learning algorithms, we explore coding strategies using events as is observed for spiking neurons in the central nervous system. Focusing on visual processing, we have previously shown that we can ...