NeurIPS Proceedings Search Link Prediction Based on Graph Neural Networks Muhan Zhang, Yixin Chen Advances in Neural Information Processing Systems 31 (NeurIPS 2018) Abstract Link prediction is a key problem for network-structured data. Link prediction heuristics use some score functions, such as common neighbors and Katz index, to measure the likelihood of links. They have obtained wide practical uses due to their simplicity, interpretability, and for some of them, scalability. However, every heuristic has
Introduction to Neural Network Verification A book by Aws Albarghouthi Deep learning has transformed the way we think of software and what it can do. But deep neural networks are fragile and their behaviors are often surprising. In many settings, we need to provide formal guarantees on the safety, security, correctness, or robustness of neural networks. This book covers foundational ideas from formal verification and their adaptation to reasoning about neural networks and deep learning. π Book in PDF an
Probabilistically rewired message-passing graph neural networks (PR-MPNNs) enhance expressive power and predictive performance by dynamically adjusting graph structures
Home AI Weirdness Book: You look like a thing About Janelle Subscribe Search Sign in Sign up AI Weirdness: the strange side of machine learning Tag: neural network Total 8 Posts Pokemon generated by neural network By Janelle Shane On July 22, 2016 - 1 min read Iβve been playing around with char-rnn, an open-source torch add-on for character-based neural networks by Andrej Karpathy [http://t.umblr.com/redirect?z=https%3A%2F%2Fgithub.com%2Fkarpathy%2Fchar-rnn&t
NeuralIntegrator: simulating spiking neural networks with discontinuities I work in the field of computational neuroscience and model spiking neural networks (SNNs) with different synaptic plasticity rules, i.e. rules o
jarxiv Japanese arxiv γ³γ³γγ³γγΈγΉγγγ γγΌγ β Robust Molecular Property Prediction via Densifying Scarce Labeled Data βItβs not a representation of meβ: Examining Accent Bias and Digital Exclusion in Synthetic AI Voice Services β How do Probabilistic Graphical Models and Graph Neural Networks Look at Network Data? ζη¨Ώζ₯: 2025εΉ΄6ζ16ζ₯ δ½ζθ : jarxiv θ¦η΄ γ°γ©γγ―
# Reduced-Precision Computation for Neural Network Training In our previous blog post, we discussed the process of training neural networks (NN) and briefly touched on NN training platforms and related memory bandwidth issues. As we noted, neural network training and inference performance are heavily contingent upon memory bandwidth. This is because the memory system is typically tasked with holding the neural network parameters β weights and biases β along with training data. With hardware optimized
The Case for GOOD Diagrams
We study training one-hidden-layer ReLU networks in the neural tangent kernel (NTK) regime, where the networks' biases are initialized to some constant rather than zero. We prove that under such initialization, the neural network will have sparse activation throughout the entire training process, which enables fast training procedures via some sophisticated computational methods. With such initialization, we show that the neural networks possess a different limiting kernel which we call \textit{bias-general
Miru Tracer, our first step towards mechanistic interpretability, performs confidence analysis and allows interaction with the token generation process.