Hacker News with Generative AI: Neural Networks

The Matrix Calculus You Need for Deep Learning (explained.ai)
Most of us last saw calculus in school, but derivatives are a critical part of machine learning, particularly deep neural networks, which are trained by optimizing a loss function.
Deep Learning, Machine Learning, Mathematics, Neural Networks
66 points by Anon84 4 days ago | 3 comments
Tied Crosscoders: Tracing How Chat LLM Behavior Emerges from Base Model (lesswrong.com)
We are interested in model-diffing: finding what is new in the chat model when compared to the base model. One way of doing this is training a crosscoder, which would just mean training an SAE on the concatenation of the activations in a given layer of the base and chat model. When training this crosscoder, we find some latents whose decoder vector mostly helps reconstruct the base model activation and does not affect the reconstruction for the chat model activation.
Generative AI, Machine Learning, AI Research, Neural Networks
7 points by aranguri 10 days ago | 0 comments
CHM Releases AlexNet Source Code (computerhistory.org)
In partnership with Google, CHM has released the source code to AlexNet, the neural network that in 2012 kick-started today’s prevailing approach to AI. It is available as open source here.
Artificial Intelligence, Open Source, Computer Science, Neural Networks, History
12 points by tosh 13 days ago | 0 comments
Neurosymbolic Decision Trees (arxiv.org)
Neurosymbolic (NeSy) AI studies the integration of neural networks (NNs) and symbolic reasoning based on logic.
Artificial Intelligence, Machine Learning, Neural Networks, Symbolic Reasoning, Decision Trees
42 points by PaulHoule 14 days ago | 0 comments
Deep Learning Is Not So Mysterious or Different (arxiv.org)
Deep neural networks are often seen as different from other model classes by defying conventional notions of generalization.
Deep Learning, Artificial Intelligence, Machine Learning, Generalization, Neural Networks
485 points by wuubuu 16 days ago | 126 comments
Arbitrary-Scale Super-Resolution with Neural Heat Fields (therasr.github.io)
Thera is the first arbitrary-scale super-resolution method with a built-in physical observation model.
Super-Resolution, Image Processing, Computer Vision, Artificial Intelligence, Neural Networks
151 points by 0x12A 18 days ago | 56 comments
Francis Crick – The Recent Excitement About Neural Networks [pdf] (1989) (wordpress.com)
Neural Networks, Artificial Intelligence, History, Science
5 points by sim04ful 22 days ago | 0 comments
Deriving Muon (jeremybernste.in)
We recently proposed Muon: a new neural net optimizer. Muon has garnered attention for its excellent practical performance: it was used to set NanoGPT speed records leading to interest from the big labs.
Machine Learning, Optimization, Neural Networks
7 points by jxmorris12 26 days ago | 3 comments
Get Started with Neural Rendering Using Nvidia RTX Kit (Vulkan) (nvidia.com)
Neural rendering is the next era of computer graphics.  By integrating neural networks into the rendering process, we can take dramatic leaps forward in performance, image quality, and interactivity to deliver new levels of immersion.
Computer Graphics, Neural Networks, Vulkan, Nvidia, Rendering
29 points by pjmlp 28 days ago | 0 comments
Analogies Between Startups and Neural Networks (mikealche.com)
I’m consulting for a company that the had a crucial team member taking “extended vacations”. Ouch!
Startups, Neural Networks, Business
10 points by yoouareperfect 35 days ago | 0 comments
Computer Simulation of Neural Networks Using Spreadsheets (2018) (arxiv.org)
The article substantiates the necessity to develop training methods of computer simulation of neural networks in the spreadsheet environment.
Neural Networks, Computer Simulation, Spreadsheets
40 points by benbreen 37 days ago | 1 comments
Z-Ant: An Open-Source SDK for Neural Network Deployment on Microprocessors (github.com/ZIGTinyBook)
Zant (Zig-Ant) is an open-source SDK designed to simplify deploying Neural Networks (NN) on microprocessors.
Open Source, Neural Networks, Microprocessors, Software Development
10 points by jedisct1 44 days ago | 0 comments
AI Designed Computer Chips That the Human Mind Can't Understand (popularmechanics.com)
A new neural network process has designed wireless chips that can outperform existing ones.
Artificial Intelligence, Computer Hardware, Neural Networks
4 points by givinguflac 60 days ago | 2 comments
An overview of gradient descent optimization algorithms (2016) (ruder.io)
Gradient descent is one of the most popular algorithms to perform optimization and by far the most common way to optimize neural networks.
Machine Learning, Optimization Algorithms, Neural Networks
135 points by skidrow 69 days ago | 26 comments
An Introduction to Neural Ordinary Differential Equations [pdf] (diposit.ub.edu)
Neural Networks, Machine Learning, Differential Equations, Mathematics
79 points by gballan 82 days ago | 10 comments
NNCP: Lossless Data Compression with Neural Networks (bellard.org)
NNCP is an experiment to build a practical lossless data compressor with neural networks.
Neural Networks, Data Compression, Machine Learning
10 points by ksec 92 days ago | 0 comments
The Structure of Neural Embeddings (seanpedersen.github.io)
A small collection of insights on the structure of embeddings (latent spaces) produced by deep neural networks.
Machine Learning, Deep Learning, Neural Networks, Embeddings
74 points by sean_pedersen 96 days ago | 4 comments
A Gentle Introduction to Graph Neural Networks (2021) (distill.pub)
Neural networks have been adapted to leverage the structure and properties of graphs. We explore the components needed for building a graph neural network - and motivate the design choices behind them.
Neural Networks, Machine Learning, Graph Theory
362 points by misonic 103 days ago | 33 comments
No More Adam: Learning Rate Scaling at Initialization Is All You Need (arxiv.org)
In this work, we question the necessity of adaptive gradient methods for training deep neural networks.
Machine Learning, Deep Learning, Optimization, Neural Networks
91 points by jinqueeny 105 days ago | 28 comments
Sequence to sequence learning with neural networks: what a decade (youtube.com)
Deep Learning, Neural Networks, Artificial Intelligence, Machine Learning
89 points by dspoka 109 days ago | 31 comments
Neuroevolution of augmenting topologies (NEAT algorithm) (wikipedia.org)
NeuroEvolution of Augmenting Topologies (NEAT) is a genetic algorithm (GA) for the generation of evolving artificial neural networks (a neuroevolution technique) developed by Kenneth Stanley and Risto Miikkulainen in 2002 while at The University of Texas at Austin.
Artificial Intelligence, Machine Learning, Evolutionary Algorithms, Neural Networks, Genetics
91 points by elsewhen 121 days ago | 33 comments
Inferring neural activity before plasticity for learning beyond backpropagation (nature.com)
For both humans and machines, the essence of learning is to pinpoint which components in its information processing pipeline are responsible for an error in its output, a challenge that is known as ‘credit assignment’.
Neural Networks, Machine Learning, Artificial Intelligence, Science
145 points by warkanlock 126 days ago | 49 comments
Quark: Real-Time, High-Resolution, and General Neural View Synthesis (quark-3d.github.io)
We present a novel neural algorithm for performing high-quality, high-resolution, real-time novel view synthesis.
Artificial Intelligence, Computer Vision, 3D Graphics, Neural Networks
27 points by lnyan 126 days ago | 1 comments
Bayesian Neural Networks (cs.toronto.edu)
Bayesian inference allows us to learn a probability distribution over possible neural networks. We can approximately solve inference with a simple modification to standard neural network tools. The resulting algorithm mitigates overfitting, enables learning from small datasets, and tells us how uncertain our predictions are.
Machine Learning, Neural Networks, Bayesian Inference
259 points by reqo 135 days ago | 54 comments
Neural Optical Flow for PIV in Fluids (synthical.com)
Neural Networks, Fluid Dynamics, Computer Vision
15 points by mixeden 144 days ago | 8 comments
Physics-informed Shadowgraph Network: End-to-end Density Field Reconstruction (arxiv.org)
This study presents a novel approach for quantificationally reconstructing density fields from shadowgraph images using physics-informed neural networks
Physics, Machine Learning, Image Processing, Neural Networks
19 points by mixeden 146 days ago | 1 comments
SharpNEAT – evolving NN topologies and weights with a genetic algorithm (sourceforge.io)
Neuroevolution of Augmenting Topologies (NEAT) is an evolutionary algorithm for evolving artificial neural networks.
Artificial Intelligence, Machine Learning, Genetic Algorithms, Neural Networks
8 points by truegoric 149 days ago | 2 comments
It all started with a perceptron (medium.com)
In homage to John Hopfield and Geoffrey Hilton, Nobel Prize winners for their “fundamental discoveries and inventions that made machine learning and artificial neural networks possible,” I propose to explore the foundations of connectionist AI.
Artificial Intelligence, Machine Learning, History, Neural Networks
30 points by thunderbong 157 days ago | 7 comments
Implementing neural networks on the "3 cent" 8-bit microcontroller (wordpress.com)
Bouyed by the surprisingly good performance of neural networks with quantization aware training on the CH32V003, I wondered how far this can be pushed. How much can we compress a neural network while still achieving good test accuracy on the MNIST dataset?
Neural Networks, Machine Learning, Microcontrollers, Embedded Systems, Image Recognition
159 points by cpldcpu 165 days ago | 20 comments
Neural Networks (MNIST inference) on the "3-cent" Microcontroller (wordpress.com)
Bouyed by the surprisingly good performance of neural networks with quantization aware training on the CH32V003, I wondered how far this can be pushed. How much can we compress a neural network while still achieving good test accuracy on the MNIST dataset?
Machine Learning, Embedded Systems, Hardware, Neural Networks
47 points by Teever 167 days ago | 0 comments