Showing results 2781-2790 of >2,855 (page 279)
https://arxiv.org/abs/2306.16830

Abstract page for arXiv paper 2306.16830: Sampling weights of deep neural networks

https://www.notebookcheck.net/Neural-networks-in-AI-less-connected-than-expected.819175.0.html

How exactly an AI, the neural network and the large language model behind it work has long been the subject of research. A surprisingly simple discovery helps to better understand the processes

https://creators.spotify.com/pod/profile/philipp-packmohr/episodes/Artificial-Neural-Networks-e4adbm/a-agv3qq

Dr. Sebastian Ritterbusch and me talk about neuronal networks at #GPN19 in Karlsruhe, Germany

https://wtfisthat.hashnode.dev/inside-a-neural-network-mlp

Understanding Feed Forward Neural Networks by Following the Information Flow

https://deepai.org/machine-learning-glossary-and-terms/recurrent-neural-network

A Recurrent Neural Network is a type of neural network that contains loops, allowing information to be stored within the network. In short, Recurrent Neural Networks use their reasoning from previous experiences to inform the upcoming events

https://codewords-test.recurse.com/issues/five/why-do-neural-networks-think-a-panda-is-a-vulture

# How to trick a neural network into thinking a panda is a vulture ### Neural networks are magical When I go to Google Photos and search my photos for ‘skyline’, it finds me this picture of the New York skyline I took in August, without me having labelled it! When I search for ‘cathedral’, Google’s neural networks find me pictures of cathedrals & churches I’ve seen. It seems magical. But of course, neural networks aren’t magic–nothing is! I recently read a paper, “Explaining and Harnessing

https://papers.nips.cc/paper/2013/hash/7b5b23f4aadf9513306bcd59afb6e4c9-Abstract.html

NeurIPS Proceedings Search Adaptive dropout for training deep neural networks Jimmy Ba, Brendan Frey Advances in Neural Information Processing Systems 26 (NIPS 2013) Abstract Recently, it was shown that by dropping out hidden activities with a probability of 0.5, deep neural networks can perform very well. We describe a model in which a binary belief network is overlaid on a neural network and is used to decrease the information content of its hidden units by selectively setting activities to zero. This ''d

https://proceedings.neurips.cc/paper_files/paper/2013/hash/7b5b23f4aadf9513306bcd59afb6e4c9-Abstract.html

NeurIPS Proceedings Search Adaptive dropout for training deep neural networks Jimmy Ba, Brendan Frey Advances in Neural Information Processing Systems 26 (NIPS 2013) Abstract Recently, it was shown that by dropping out hidden activities with a probability of 0.5, deep neural networks can perform very well. We describe a model in which a binary belief network is overlaid on a neural network and is used to decrease the information content of its hidden units by selectively setting activities to zero. This ''d

https://www.emergentmind.com/topics/neural-topic-models-ntms

Neural Topic Models (NTMs) harness deep neural networks to reveal hidden themes in massive text corpora, enabling scalable and flexible analysis

https://www.sicpers.info/2019/01/structured-pruning-of-deep-convolutional-neural-networks/

Structured Pruning of Deep Convolutional Neural Networks , Sajid Anwar et al. In the ACM Journal on Emerging Technologies in Computing special issue on hardware and algorithms for learning-on-a-chip, May 2017. ## Notes Quick, a software engineer mentions a “performance” problem to you. What do they mean? This is, of course, an unfair question. There are too many different ideas that all get branded “performance” for us to know what we are trying to solve. This paper is simultaneously about two

‹ Prev Next ›