ICYMI: Facebook researchers open sourced PyRobot, a lightweight, high-level interface that lets AI researchers get up and running with robotics experiments in just hours. No specialized robotics expertise needed!

https://www.profillic.com/paper/arxiv:1906.08236

Distributed Deep Learning Pipelines with PySpark and Keras
https://towardsdatascience.com/distributed-deep-learning-pipelines-with-pyspark-and-keras-a3a1c22b9239

The Functional Neural Process
Louizos et al.: https://arxiv.org/abs/1906.08324
#ArtificialIntelligence #Bayesian #MachineLearning

A scientist at Google Brain devised a way for a machine-learning system to teach itself about how the world works. His name is Ian Goodfellow, and he was one of our 35 Innovators Under 35 in 2017. This year's list comes out on June 25. Stay tuned for the 35 inventors, entrepreneurs, visionaries, humanitarians, and pioneers who will shape tomorrow's technology.
https://www.technologyreview.com/lists/innovators-under-35/2017/inventor/ian-goodfellow/

Unsupervised State Representation Learning in Atari

Learn representations by maximizing mutual information across spatiotemporal features of observations:

https://arxiv.org/abs/1906.08226

resnext101_32x8d_wsl: the ConvNet pre-trained on Instagram hashtags and fine-tuned on ImageNet, yielding a record-breaking 85.4% top-1 accuracy is now available.

https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/

High precision coding in mouse visual cortex

Stringer et al.: https://www.biorxiv.org/content/biorxiv/early/2019/06/21/679324.full.pdf

#brain #cortex #neurons

An early version of fastai for Swift for Tensorflow

"Would you like to train xresnet using 1cycle training on Imagenette, using fastai and the data blocks API?

IN SWIFT?!?

Now you can." - Jeremy Howard

GitHub: https://github.com/fastai/harebrain

#swift #tensorflow #naturallanguage #machinelearning

CS294-158 Deep Unsupervised Learning Spring 2019

Instructors: Pieter Abbeel, Peter Chen, Jonathan Ho, Aravind Srinivas - https://sites.google.com/view/berkeley-cs294-158-sp19/home

#unsupervisedlearning #machinelearning #deeplearning

Find The Most Updated and Free Resources of Artificial Intelligence, Machine Learning, Data Science, Deep Learning, Mathematics, Python, and R Programming.



https://www.marktechpost.com/free-resources/

Troubleshooting Deep Neural Networks

A Field Guide to Fixing Your Model

Slides by Josh Tobin: https://josh-tobin.com/assets/pdf/troubleshooting-deep-neural-networks-01-19.pdf

#ArtificialIntelligence #DeepLearning #MachineLearning

Calibrated Model-Based Deep Reinforcement Learning

https://arxiv.org/abs/1906.08312v1

A Survey of Optimization Methods from a Machine Learning Perspective

https://arxiv.org/abs/1906.06821v1

Shaping Belief States with Generative Environment Models for RL

Gregor et al.: https://arxiv.org/abs/1906.09237v2

#RL #SelfSupervised #GenerativeWorldModels #BeliefStates

One of our best of #cvpr2019 is @NvidiaAI STEAL - a new semantic boundary detector for precisely detecting & predicting where an object begins & ends -outperforming past works. A really intelligent way to refine segmentation datasets and train better segmentation models

Read at https://arxiv.org/pdf/1904.07934.pdf
code(@PyTorch):github.com/nv-tlabs/STEAL

ICYMI from CVPR 2019: Microsoft researchers use GANs to generate images and storyboards from captions

The proposed Obj-GAN significantly outperforms the previous state of the art in various metrics on the large-scale COCO benchmark

https://www.profillic.com/paper/arxiv:1902.10740

Also, check out previously released, StoryGAN

(capable of generating comic-like storyboards from multi-sentence paragraphs)

https://www.profillic.com/paper/arxiv:1812.02784

Speech Recognition using Artificial Neural Network (ANN)
https://www.aitimejournal.com/@monisha.m/speech-recognition-using-artificial-neural-networkann