Parallel and Distributed Deep Learning: A Survey
https://towardsdatascience.com/parallel-and-distributed-deep-learning-a-survey-97137ff94e4c

Best of (link: https://arXiv.org) arXiv.org for AI, Machine Learning, and Deep Learning – March 2019

https://insidebigdata.com/2019/04/09/best-of-arxiv-org-for-ai-machine-learning-and-deep-learning-march-2019/

Survey on Automated Machine Learning. (link: https://arxiv.org/abs/1904.12054) arxiv.org/abs/1904.12054

Real numbers, data science and chaos: How to fit any dataset with a single parameter

Laurent Boué: https://arxiv.org/abs/1904.12320

Code: https://github.com/Ranlot/single-parameter-fit/

#artificialintelligence #datascience #dataset #machinelearning

Statistical Physics of Liquid Brains


Liquid neural nets (or “liquid brains”) – class of cognitive living networks
characterised by the agents (ants or immune cells, for example) moving in space are compared with standard neural nets

https://www.biorxiv.org/content/10.1101/478412v1

A scientist at Google Brain devised a way for a machine-learning system to teach itself about how the world works.

https://www.technologyreview.com/lists/innovators-under-35/2017/inventor/ian-goodfellow/

Best Deep Learning Courses: Updated for 2019


https://blog.floydhub.com/best-deep-learning-courses-updated-for-2019/

https://t.iss.one/ArtificialIntelligenceArticles

[Course]Deep reinforcement learning, provided by Prof. Sergey Levine at UC Berkeley


https://www.youtube.com/playlist?list=PLkFD6_40KJIxJMR-j5A1mkxK26gh_qg37&fbclid=IwAR2xoZGCYu4-HBBODMVSjKCHAqNMkl3zMTZ6OpgFcB9zbOSyMLQhNlbdd_g

To find out which sights specific neurons in monkeys "like" best, researchers designed an algorithm, called XDREAM, that generated images that made neurons fire more than any natural images the researchers tested. As the images evolved, they started to look like distorted versions of real-world stimuli. The work appears May 2 in the journal Cell

https://medicalxpress.com/news/2019-05-trippy-images-ai-super-stimulate-monkey.html

Have you ever wondered what it might sound like if the Beatles jammed with Lady Gaga or if Mozart wrote one more masterpiece? This machine learning algorithm offers an answer, of sorts.
https://www.technologyreview.com/s/613430/this-ai-generated-musak-shows-us-the-limit-of-artificial-creativity/

What if deep learning could be your personal stylist? Enter Fashion++, a deep image generation neural network that learned to synthesize clothing and suggest minor edits to make an outfit more fashionable 👔 👠 Read the full paper by Wei-Lin Hsiao et al: https://bit.ly/2LgWiD6

Self-Supervision and Play
Pierre Sermanet et al.: https://docs.google.com/presentation/d/145wBH7TEJoEclVzE1YKTihqIXWMljeNIA6ozwMZLb3Q/edit#slide=id.g581ee82d09_0_517
#DeepLearning #Robotics #UnsupervisedLearning

Study shows that artificial neural networks can be used to drive brain activity

https://medicalxpress.com/news/2019-05-artificial-neural-networks-brain.html

https://t.iss.one/ArtificialIntelligenceArticles

Videos and lectures on MachineLearning DataScience and informatics

Ryan Urbanowicz

Perelman School of Medicine at the University of Pennsylvania

https://www.med.upenn.edu/urbslab/videos.html

Neural Path Planning: Fixed Time, Near-Optimal Path Generation via Oracle Imitation
Bency et al.: https://arxiv.org/abs/1904.11102

#Robotics #ArtificialIntelligence #MachineLearning

A Mean Field Theory of Batch Normalization
Yang et al.: https://arxiv.org/abs/1902.08129

#ArtificialIntelligence #NeuralComputing #NeuralNetworks #MachineLearning #DynamicalSystems

Spectral Inference Networks (SpIN)
Paper by Pfau et al.: https://arxiv.org/abs/1806.02215
Code: https://github.com/deepmind/spectral_inference_networks

#MachineLearning #DeepLearning #ArtificialIntelligence

A new critique of deep-learning systems that use neural nets skewers some of the current AI hype.


https://www.technologyreview.com/f/609875/the-case-against-deep-learning-hype/

SafeML ICLR 2019 Workshop
Accepted Papers: https://sites.google.com/view/safeml-iclr2019/accepted-papers

#ArtificialIntelligence #AISafety #MachineLearning
@ArtificialIntelligenceArticles

"Billion-scale semi-supervised learning for image classification"
by I. Zeki Yalniz, Hervé Jégou, Kan Chen, Manohar Paluri, Dhruv Mahajan.

Weakly-supervised pre-training + semi-supervised pre-training + distillation + transfer/fine-tuning =
81.2% twith ResNet-50,
84.8% with ResNeXt-101-32x16,
top-1 accuracy on ImageNet.

ArXiv: https://arxiv.org/abs/1905.00546

Brought to you by Facebook AI.

Original post by Yalniz Zeki: https://www.facebook.com/i.zeki.yalniz/posts/10157311492509962

@ArtificialIntelligenceArticles

#weekend_read
Paper-Title: Reinforcement Learning, Fast and Slow
#Deepmind #Cognitive_Science
Link to the paper: https://www.cell.com/action/showPdf?pii=S1364-6613%2819%2930061-0

TL;DR: [1] This paper reviews recent techniques in deep RL that narrow the gap in learning speed between humans and agents, & demonstrate an interplay between fast and slow learning w/ parallels in animal/human cognition.
[2] When episodic memory is used in reinforcement learning, an explicit record of past events is maintained for making decisions about the current situation. The action chosen is the one associated with the highest value, based on the outcomes of similar past situations.
[3] Meta-reinforcement learning quickly adapts to new tasks by learning strong inductive biases. This is done via a slower outer learning loop training on the distribution of tasks, leading to an inner loop that rapidly adapts by maintaining a history of past actions and observations.