Machine learning must always balance flexibility and prior assumptions about the data. In neural networks, the network architecture codifies these prior assumptions, yet the precise relationship between them is opaque. Deep learning solutions are therefore difficult to build without a lot of trial and error, and neural nets are far from an out-of-the-box solution for most applications

This paper introduces a tensor neural network (TNN) to address nonparametric regression problems, leveraging its distinct sub-network structure to effectively facilitate variable separation and enhance the approximation of complex, high-dimensional functions. The TNN demonstrates superior performance compared to conventional Feed-Forward Networks (FFN) and Radial Basis Function Networks (RBN) in terms of both approximation accuracy and generalization capacity, even with a comparable number of parameters. A

Artificial neural networks (ANNs) are a type of information processing system based on mimicking the principles of biological brains, and have been broadly applied in application domains such as pattern recognition, automatic control, signal processing, decision support systems and artificial intelligence. Spiking neural networks (SNNs) are a type of biologically inspired ANN that perform information processing based on discrete time spikes. They are more biologically realistic than classic ANNs, and can po

Oak Lab Research Event-driven neural networks with batch-size one learning algorithms Coming soon Coming soon. Oak Lab © 2026

Learn how to enable long short-term memory, convolutional neural, and recurrent neural networks on top of TensorFlow to describe what is shown in the picture

← A Spatio-temporal Aligned SUNet Model for Low-light Video Enhancement Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach → # Modelling the Human Intuition to Complete the Missing Information in Images for Convolutional Neural Networks この研究では、直観をモデル化し

neural networks research group Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel (2020) Neural Networks (NNs) have been extensively used for a wide spectrum of real-world regression tasks, where the goal is to predict a numerical outcome such as revenue, effectiveness, or a quantitative result. In many such tasks, the point prediction is not enough: the uncertainty (i.e. risk or confidence) of that prediction must also be estimated. Standard NNs, which

This tutorial builds on ml5.neuralNetwork() videos examining raw pixels as inputs to a neural network. This sets the stage for a discussion on convolutional neural networks

Optimizing neural networks and large language models (LLMs) is all about smart strategies like pruning, quantization, and knowledge distillation to shrink model size and speed up computation without sacrificing performance. These cutting-edge techniques streamline deep learning models, making them faster, more efficient, and ready for real-world deployment on everything from mobile devices to high-performance servers

Abstract page for arXiv paper 1601.04589: Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis