using #machine-learning and #neural-networks to generate cost models for #compilers targeting #tensor-processing-units #PDF #paper
on 02024-12-12nice #PDF slide deck about histogram filters, similar to #particle-filters, with Octave code to implement it. #algorithms #machine-learning
on 02023-10-07#introduction series of videos on #machine-learning, discussion thread
on 02017-05-19Trip report to NIPS 2016 (Neural Information Processing Systems, i.e. #neural-networks) in December. Sections on GANs, deep reinforcement learning, Bayesian deep learning. #machine-learning
on 02017-03-11The first chapter of the famed "UFLDL Tutorial" #ebook (“Unsupervised Feature Learning and Deep Learning”) on #machine-learning covers linear regression; later it covers #deep-learning and other #neural-networks.
on 02017-01-14Ian Goodfellow’s #ebook on #deep-learning #neural-networks; supposedly the most comprehensive available. Goodfellow is the guy who invented GANs I think. #machine-learning
on 02017-01-03Robin Hanson is skeptical of #AI claims about current #machine-learning algorithms.
on 02016-12-07#paper on #DCGANs (variety “introspective adversarial networks”) for photo editing. #deep-learning #neural-networks #GANs #machine-learning
on 02016-10-03#machine-learning exercises form Andrew #Ng’s course in Python.
on 02016-08-13Discussion thread on #machine-learning exercises in Python, commenting specifically on Andrew #Ng’s course (originally in Octave)
on 02016-08-13discussion thread largely about how to learn about #machine-learning
on 02016-06-27an overview of "generative models" such as #DCGANs. #machine-learning
on 02016-06-21A 15-hour #video #MOOC on #machine-learning from 2014 with an #ebook
on 02016-06-21#ebook on #reinforcement-learning #machine-learning
on 02016-06-21an update on the state of the art of #reinforcement-learning by #Karpathy. #AI #deep-learning #machine-learning #toread
on 02016-06-21“Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks”, by Alec Radford, Luke Metz, and Soumith Chintala, generated realistic images of bedrooms with convolutional #deep-learning #neural-networks by simultaneously training two networks in a sort of Turing test: one that tried to generate realistic images of bedrooms and one that tried to distinguish between the real images and fake ones. They call this technique "DCGANs". #GANs #machine-learning
on 02016-05-24a “non-technical” #introduction to #machine-learning.
on 02016-03-29Leaf is a #machine-learning #deep-learning #neural-networks system in Rust.
on 02016-03-08an encyclopedia of Brown University has been automatically hypertextified using #machine-learning natural-language processing.
on 02015-12-12#Tesla drivers are training a #machine-learning autopilot for their now #self-driving cars — providing A MILLION MILES A DAY of training data. I’m imagining Elon Musk saying, “Bite me, Google.”
on 02015-12-072001 #pdf #paper introducing "random forests", which is rumored to be the most versatile #machine-learning algorithm. Unfortunately, the author trademarked the name, so you probably have to call it something else if you implement it.
on 02015-11-22"Neural Programmer" doing #machine-learning of programs with #neural-networks. Part of the “Google Brain” project.
on 02015-11-18#machine-learning of faces (with #neural-nets) used to generate faces, sort of like Deep Dream.
on 02015-11-17#Random-forests may be #powerful-primitives for #machine-learning.
on 02015-11-16Jeff Dean talks about the #TensorFlow #machine-learning system as part of his keynote last week at BayLearn15 about machine learning.
on 02015-11-10#pandas #Python vs. #R. includes things like #random-forest modeling, linear regression, and web scraping #machinelearning
on 02015-10-14An #introduction to conditional random fields. #machine-learning "CRF Introduction"
on 02015-08-23Another #trading #algorithms #paper by the same authors as the 2011 paper: “Efficient market making via convex optimization, and a connection to online learning (2012)”. Talks about Arrow-Debreu #prediction-markets as a market-based probability estimator and draws a connection to online #machine-learning algorithms, and briefly links to computational #complexity results. The reason the authors are interested in automated market-making seems to be that it is needed to make #prediction markets over complex outcome spaces feasibly liquid.
on 02015-08-13A #machine-learning #neural-network in 11 lines of #Python. #smallisbeautiful
on 02015-08-05Commentary on Breiman's #statistics vs. #machine-learning (more or less) paper
on 02015-08-05#Statistics vs. #machine-learning: the same thing really
on 02015-08-05