AI Medical Compendium Journal:
Neural computation

Showing 31 to 40 of 203 articles

Feature Extraction of Surface Electromyography Based on Improved Small-World Leaky Echo State Network.

Neural computation
Surface electromyography (sEMG) is an electrophysiological reflection of skeletal muscle contractile activity that can directly reflect neuromuscular activity. It has been a matter of research to investigate feature extraction methods of sEMG signals...

Evaluating the Potential Gain of Auditory and Audiovisual Speech-Predictive Coding Using Deep Learning.

Neural computation
Sensory processing is increasingly conceived in a predictive framework in which neurons would constantly process the error signal resulting from the comparison of expected and observed stimuli. Surprisingly, few data exist on the accuracy of predicti...

Improving Generalization via Attribute Selection on Out-of-the-Box Data.

Neural computation
Zero-shot learning (ZSL) aims to recognize unseen objects (test classes) given some other seen objects (training classes) by sharing information of attributes between different objects. Attributes are artificially annotated for objects and treated eq...

From Synaptic Interactions to Collective Dynamics in Random Neuronal Networks Models: Critical Role of Eigenvectors and Transient Behavior.

Neural computation
The study of neuronal interactions is at the center of several big collaborative neuroscience projects (including the Human Connectome Project, the Blue Brain Project, and the Brainome) that attempt to obtain a detailed map of the entire brain. Under...

Replicating Neuroscience Observations on ML/MF and AM Face Patches by Deep Generative Model.

Neural computation
A recent paper (Chang & Tsao, 2017) reports an interesting discovery. For the face stimuli generated by a pretrained active appearance model (AAM), the responses of neurons in the areas of the primate brain that are responsible for face recognition ...

Reinforcement Learning in Spiking Neural Networks with Stochastic and Deterministic Synapses.

Neural computation
Though succeeding in solving various learning tasks, most existing reinforcement learning (RL) models have failed to take into account the complexity of synaptic plasticity in the neural system. Models implementing reinforcement learning with spiking...

Integrating Flexible Normalization into Midlevel Representations of Deep Convolutional Neural Networks.

Neural computation
Deep convolutional neural networks (CNNs) are becoming increasingly popular models to predict neural responses in visual cortex. However, contextual effects, which are prevalent in neural processing and in perception, are not explicitly handled by cu...

Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning.

Neural computation
Humans are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed , is one of the major r...

On Functions Computed on Trees.

Neural computation
Any function can be constructed using a hierarchy of simpler functions through compositions. Such a hierarchy can be characterized by a binary rooted tree. Each node of this tree is associated with a function that takes as inputs two numbers from its...

Mutual Inhibition with Few Inhibitory Cells via Nonlinear Inhibitory Synaptic Interaction.

Neural computation
In computational neural network models, neurons are usually allowed to excite some and inhibit other neurons, depending on the weight of their synaptic connections. The traditional way to transform such networks into networks that obey Dale's law (i....