GFlowOut uses generative flow networks to improve Bayesian inference for dropout masks in deep neural networks, enhancing calibration and uncertainty estimation

CSP Test --> Main Navigation ICLR Help/FAQ Contact ICLR Create Profile Code of Conduct Journal To Conference Track Diversity & Inclusion Proceedings at OpenReview Future Meetings Press Exhibitor Information ICLR Blog ICLR Twitter About ICLR Downloads Privacy Policy Reset Password My Stuff Login Organizers Select Year: (2023) 2027 2026 2025 2024 2023 2022 2021 2020 2019 2018 2017 2016 2015 2014 2013 Virtual presentation / poster accept Sequential Learning of Neural Networks for Prequential MDL Jorg Bornschei

Chair for Verification and Synthesis of Reactive Systems Teaching Temporal Logics to Neural Networks Christopher Hahn , Frederik Schmitt , Jens Kreber, Markus N. Rabe and Bernd Finkbeiner PDF We study two fundamental questions in neuro-symbolic computing: can deep learning tackle challenging problems in logics end-to-end, and can neural networks learn the semantics of logics. In this work we focus on linear-time temporal logic (LTL), as it is widely used in verification. We train a Transformer on the proble

Abstract page for arXiv paper 2409.02682: Symmetries and synchronization from whole-neural activity in {\it C. elegans} connectome: Integration of functional and structural networks

Everything seems ok with my code (accuracy of the deep res net is 97%), but the test from outputs import ResNet50_summary model = ResNet50(input_shape = (64, 64, 3), classes = 6) comparator(summary(model), ResNet50_summ…

Guide to Machine Learning vs Neural Network. Here we discussed its key differences with infographics, & comparison table in a simple manner

In this post, we will study inductive biases of the parameter-function map of random neural networks using star domain volume estimates. This builds on the ideas introduced in Estimating the Probability of Sampling a Trained Neural Network at Random and Neural Redshift: Random Networks are not Random Functions (henceforth NRS). Inductive biases To understand generalization in deep neural networks, we must understand inductive biases. Given a fixed architecture, some tasks will be easily learnable, while oth

Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are typically local and treat GNNs as black-boxes. They do not look inside the model, inhibiting human trust in the model and explanations. Motivated by the ability of neurons to detect high-level semantic concepts in vision models, we perform a novel analysis on the behaviour of individual GNN neurons to answer questions about GNN int

The evolution of neural sequence prediction, and how it connects to classical methods

NeurIPS Proceedings Search Feature-Learning Networks Are Consistent Across Widths At Realistic Scales Nikhil Vyas, Alexander Atanasov, Blake Bordelon, Depen Morwani, Sabarish Sainathan, Cengiz Pehlevan Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track Abstract We study the effect of width on the dynamics of feature-learning neural networks across a variety of architectures and datasets. Early in training, wide neural networks trained on online data have not only ident