neural network – Page 13 – Andrew Fairless, Ph.D.

What I Read: Challenging AI to Learn Better

By Andrew Fairless on September 20, 2022August 22, 2022

https://www.quantamagazine.org/the-computer-scientist-trying-to-teach-ai-to-learn-like-we-do-20220802/ The Computer Scientist Challenging AI to Learn BetterAllison WhittenContributing WriterAugust 2, 2022Christopher Kanan is building algorithms that can continuously learn over time — the way we do. “Instead ofContinue readingWhat I Read: Challenging AI to Learn Better

What I Read: BLOOM Training

By Andrew Fairless on September 12, 2022August 3, 2022

https://huggingface.co/blog/bloom-megatron-deepspeed The Technology Behind BLOOM TrainingStas BekmanPublished July 14, 2022. “…training ever larger language models has become the norm… the hidden knowledge about how to train such models rarely getsContinue readingWhat I Read: BLOOM Training

What I Read: Transformers in computer vision

By Andrew Fairless on September 6, 2022August 3, 2022

https://theaisummer.com/transformers-computer-vision/ Transformers in computer vision: ViT architectures, tips, tricks and improvementsNikolas Adaloglouon2021-10-21 “You are probably already aware of the Vision Transformer (ViT)…. We will address questions like how can youContinue readingWhat I Read: Transformers in computer vision

What I Read: Neural-Implicit Representations, 3D Shapes

By Andrew Fairless on August 2, 2022July 8, 2022

https://towardsdatascience.com/neural-implicit-representations-for-3d-shapes-and-scenes-c6750dff49db?gi=dd4876367dbb Neural-Implicit Representations for 3D Shapes and ScenesOmri KaduriJun 26 “Tracing the progress of deep learning-based solutions to computer graphics tasks”

What I Read: Annotated Diffusion Model

By Andrew Fairless on August 1, 2022June 27, 2022

https://huggingface.co/blog/annotated-diffusion The Annotated Diffusion ModelPublished June 7th, 2022Niels RoggeKashif Rasul “In this blog post, we’ll take a deeper look into Denoising Diffusion Probabilistic Models… as researchers have been able toContinue readingWhat I Read: Annotated Diffusion Model

What I Read: Text Embeddings Visually Explained

By Andrew Fairless on July 26, 2022July 8, 2022

https://txt.cohere.ai/text-embeddings/ Text Embeddings Visually ExplainedMeor AmerJun 28, 2022 “We take a visual approach to gain an intuition behind text embeddings, what use cases they are good for, and how theyContinue readingWhat I Read: Text Embeddings Visually Explained

What I Read: Make the Universe Think

By Andrew Fairless on July 13, 2022June 27, 2022

https://www.quantamagazine.org/how-to-make-the-universe-think-for-us-20220531/ How to Make the Universe Think for UsCharlie WoodStaff WriterMay 31, 2022 “Physicists are building neural networks out of vibrations, voltages and lasers, arguing that the future of computingContinue readingWhat I Read: Make the Universe Think

What I Read: Bandits for Recommender Systems

By Andrew Fairless on June 8, 2022May 23, 2022

https://eugeneyan.com/writing/bandits/ Bandits for Recommender Systemseugeneyan “Recommender systems work well when we have a lot of data on user-item preferences…. Conversely, with very little data, we have low certainty…. Bandits addressContinue readingWhat I Read: Bandits for Recommender Systems

What I Read: ‘Machine Scientists’ Distill the Laws of Physics From Raw Data

By Andrew Fairless on June 7, 2022May 23, 2022

https://www.quantamagazine.org/machine-scientists-distill-the-laws-of-physics-from-raw-data-20220510/ Powerful ‘Machine Scientists’ Distill the Laws of Physics From Raw DataCharlie WoodStaff WriterMay 10, 2022 “Researchers say we’re on the cusp of “GoPro physics,” where a camera can pointContinue readingWhat I Read: ‘Machine Scientists’ Distill the Laws of Physics From Raw Data

What I Read: Beyond Message Passing, Graph Neural Networks

By Andrew Fairless on June 6, 2022May 23, 2022

https://thegradient.pub/graph-neural-networks-beyond-message-passing-and-weisfeiler-lehman/ Beyond Message Passing: a Physics-Inspired Paradigm for Graph Neural NetworksMichael Bronstein07.May.2022 “…the “node and edge-centric” mindset of current graph deep learning schemes imposes strong limitations… we propose physics-inspired “continuous”Continue readingWhat I Read: Beyond Message Passing, Graph Neural Networks

Tag: neural network