neural networks – BunnyStomp

https://neurolaunch.com/connectionism-psychology/

90

Connectionism Psychology: Neural Networks in Mental Processes

Discover connectionism psychology: how neural networks model the mind differently from symbolic AI. Explore learning, memory, and cognition through dist

https://www.obitko.com/tutorials/neural-network-prediction/interactive-example-nasdaq.html

87

Prediction with Neural Networks: NASDAQ Example

Interactive neural network demo for NASDAQ stock index prediction. Train the network on historical NASDAQ data and observe prediction accuracy

https://paperswithcode.co/paper/2410.04209

86

Equivariant Neural Functional Networks for Transformers (arXiv:2410.04209) | Papers with Code

This paper systematically explores neural functional networks (NFN) for transformer architectures. NFN are specialized neural networks that treat the weights, gradients, or

https://zjykzj.cn/posts/9def5d9f.html

86

Learning both Weights and Connections for Efficient Neural Networks | 大海

原文地址：Learning both Weights and Connections for Efficient Neural Networks

https://research.google/blog/inceptionism-going-deeper-into-neural-networks/

89

Inceptionism: Going Deeper into Neural Networks

Posted by Alexander Mordvintsev, Software Engineer, Christopher Olah, Software Engineering Intern and Mike Tyka, Software EngineerUpdate - 13/07/20...

https://turinglang.org/docs/tutorials/bayesian-neural-networks/index.html

91

Bayesian Neural Networks – Turing.jl

v0.46 Getting Started Core Functionality User Guide Automatic Differentiation MCMC Sampling Options Submodels Custom Distributions Querying Model Probabilities Modifying the Log Probability External Likelihoods Tracking Extra Quantities Predictive Distributions Mode Estimation Threadsafe Evaluation Performance Tips Sampler Visualization Using DynamicHMC VarNamedTuple Vectorisation of Turing models Using External Samplers Debugging Models Troubleshooting Tutorials Introduction: Coin Flipping Gaussian Mixture

https://www.emergentmind.com/papers/1711.00811

89

Expressive power of recurrent neural networks

Deep neural networks are surprisingly efficient at solving practical tasks, but the theory behind this phenomenon is only starting to catch up with the practice. Numerous works show that depth is the key to this efficiency. A certain class of deep convolutional networks -- namely those that correspond to the Hierarchical Tucker (HT) tensor decomposition -- has been proven to have exponentially higher expressive power than shallow networks. I.e. a shallow network of exponential width is required to realize t

https://harshith.org/recurrent-neural-networks-rnn-vs-transformers-which-should-you-choose-for-sequential-data/

98

Recurrent Neural Networks (RNN) vs Transformers: Which Should You Choose for Sequential Data? – Harshith AI Portal

>� Harshith AI Portal Your Comprehensive AI Resource Hub Home › Deep Learning › Article Deep Learning Recurrent Neural Networks (RNN) vs Transformers: Which Should You Choose for Sequential Data? 👤 By Harshith M R 📅 Jan 28, 2026 ⏱️ 18 min read 💬 0 Comments 📑 Table of Contents Jump to sections as you read... Recurrent Neural Networks (RNN) vs Transformers: Which Should You Choose for Sequential Data? Meta Description: Compare RNNs, LSTMs, GRUs, and Transformers for sequential data

https://moldstud.com/articles/p-optimize-neural-networks-for-edge-computing-essential-techniques-and-best-practices

84

Optimize Neural Networks for Edge Computing - Essential Techniques and Best Practices | MoldStud

Reducing the size of neural network models is crucial for their effective deployment on edge devices

https://www.tensortonic.com/ml-math/graph-theory/gnn-intro

89

Introduction to Graph Neural Networks (GNNs) | TensorTonic

Neural networks for graph data. Learn node embeddings, message passing, aggregation functions, and GNN architectures like GCN and GAT