DreamTeam/Reading - Revision history

Fnord: /* Symbolic Mathematics */

2020-01-09T07:02:00Z

Symbolic Mathematics

← Older revision		Revision as of 00:02, 9 January 2020
Line 50:		Line 50:

	https://arxiv.org/pdf/1912.01412.pdf -- "Deep Learning for Symbolic Mathematics"		https://arxiv.org/pdf/1912.01412.pdf -- "Deep Learning for Symbolic Mathematics"

			https://www.scottaaronson.com/busybeaver.pdf -- "A Relatively Small Turing Machine Whose Behavior Is Independent of Set Theory"

			https://www.scottaaronson.com/blog/?p=2725 -- "The 8000th Busy Beaver number eludes ZF set theory: new paper by Adam Yedidia and me"

	== Vision ==		== Vision ==

2019-12-29T04:52:24Z

← Older revision		Revision as of 21:52, 28 December 2019
Line 41:		Line 41:

	https://arxiv.org/abs/1803.03635 -- "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" Jonathan Frankle, Michael Carbin		https://arxiv.org/abs/1803.03635 -- "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" Jonathan Frankle, Michael Carbin

			== Global Workspace Theory ==

			http://bernardbaars.pbworks.com/f/BaarsJCS1997.pdf -- "IN THE THEATRE OF CONSCIOUSNESS"


	== Symbolic Mathematics ==		== Symbolic Mathematics ==

2019-12-19T05:56:11Z

Language Models

← Older revision		Revision as of 22:56, 18 December 2019
Line 75:		Line 75:

	https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/models/transformer.py - "official" implementation of "Attention Is All You Need"		https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/models/transformer.py - "official" implementation of "Attention Is All You Need"

			https://jalammar.github.io/illustrated-gpt2/ - The Illustrated GPT-2 (Visualizing Transformer Language Models)

	== Bioengineering ==		== Bioengineering ==

2019-12-05T04:53:23Z

← Older revision		Revision as of 21:53, 4 December 2019
Line 40:		Line 40:
	http://radicalsciencenews.org/599-2/ -- "Deep Learning Fuels Nvidia’s Self-Driving Car Technology"		http://radicalsciencenews.org/599-2/ -- "Deep Learning Fuels Nvidia’s Self-Driving Car Technology"

	~~== Sparsity ==~~		https://arxiv.org/abs/1803.03635 -- "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" Jonathan Frankle, Michael Carbin

	https://arxiv.org/~~abs~~/~~1803~~.~~03635~~ -- "~~The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks~~" ~~Jonathan Frankle, Michael Carbin~~		== Symbolic Mathematics ==

			https://arxiv.org/pdf/1912.01412.pdf -- "Deep Learning for Symbolic Mathematics"

	== Vision ==		== Vision ==

2019-09-12T03:58:05Z

← Older revision		Revision as of 20:58, 11 September 2019
Line 39:		Line 39:

	http://radicalsciencenews.org/599-2/ -- "Deep Learning Fuels Nvidia’s Self-Driving Car Technology"		http://radicalsciencenews.org/599-2/ -- "Deep Learning Fuels Nvidia’s Self-Driving Car Technology"

			== Sparsity ==

			https://arxiv.org/abs/1803.03635 -- "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" Jonathan Frankle, Michael Carbin

	== Vision ==		== Vision ==

2019-09-12T03:23:25Z

← Older revision		Revision as of 20:23, 11 September 2019
Line 4:		Line 4:

	==Websites and events that have piqued our interest==		==Websites and events that have piqued our interest==

			http://cs375.stanford.edu/ -- Dan Yamins Large-Scale Neural Network Models for Neuroscience CS375

	https://faculty.washington.edu/chudler/facts.html -- brain facts		https://faculty.washington.edu/chudler/facts.html -- brain facts

2019-09-05T03:15:19Z

Language Models

← Older revision		Revision as of 20:15, 4 September 2019
Line 43:		Line 43:

	== Language Models ==		== Language Models ==

			https://blog.scaleway.com/2019/building-a-machine-reading-comprehension-system-using-the-latest-advances-in-deep-learning-for-nlp/ -- "Natural Language Processing: the age of Transformers"

	https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf -- "Language Models are Unsupervised Multitask Learners"		https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf -- "Language Models are Unsupervised Multitask Learners"

2019-08-01T05:59:51Z

Language Models

← Older revision		Revision as of 22:59, 31 July 2019
Line 57:		Line 57:

	https://github.com/rowanz/grover - grover GPU/TPU based GPT-2 transformer implementation		https://github.com/rowanz/grover - grover GPU/TPU based GPT-2 transformer implementation

			https://arxiv.org/pdf/1905.12616.pdf -- "Defending Against Neural Fake News"

	https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html - blog post on attention		https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html - blog post on attention

2019-07-18T04:55:58Z

Websites and events that have piqued our interest

← Older revision		Revision as of 21:55, 17 July 2019
Line 4:		Line 4:

	==Websites and events that have piqued our interest==		==Websites and events that have piqued our interest==

			https://faculty.washington.edu/chudler/facts.html -- brain facts

	http://onlinehub.stanford.edu/cs224 -- Natural Language Processing with Deep Learning		http://onlinehub.stanford.edu/cs224 -- Natural Language Processing with Deep Learning

2019-07-18T03:47:36Z

Language Models

← Older revision		Revision as of 20:47, 17 July 2019
Line 47:		Line 47:

	https://arxiv.org/pdf/1705.03122.pdf -- "Convolutional Sequence to Sequence Learning"		https://arxiv.org/pdf/1705.03122.pdf -- "Convolutional Sequence to Sequence Learning"

			https://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf -- "Sequence to Sequence Learning with Neural Networks"

	https://arxiv.org/pdf/1508.07909.pdf -- "Neural Machine Translation of Rare Words with Subword Units"		https://arxiv.org/pdf/1508.07909.pdf -- "Neural Machine Translation of Rare Words with Subword Units"