This paper introduces a new method to play SuperMario Bros. using RL agent and without knowing the scores from the environment (pure exploration). They employ optical flow for evaluating the novelty of states to guide the RL agent.

https://www.profillic.com/paper/arxiv:1905.10071

In 2017, Google announced a Tensor Processing Unit (#TPU) — a custom application-specific integrated circuit (ASIC) built specifically for #machinelearning. A year later, TPUs were moved to the cloud and made open for commercial use.

Following the line of CPUs and GPUs, Tensor Processing Units (TPUs) are Google’s custom-developed application-specific integrated circuits (ASICs) that are supposed to accelerate machine learning workloads. They are designed specifically for Google’s #TensorFlow framework, a symbolic math library that is used for #neuralnetworks.

https://medium.com/sciforce/understanding-tensor-processing-units-10ff41f50e78

SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
Fedorov et al.: https://arxiv.org/pdf/1905.12107.pdf
#ArtificialIntelligence #DeepLearning #MachineLearning

These Insect-Inspired Robots Don't Need GPS For Orientation
https://www.humanbrainproject.eu/en/follow-hbp/news/these-insect-inspired-robots-don-t-need-gps-for-orientation

Theoretical Physics for Deep Learning
https://sites.google.com/view/icml2019phys4dl https://t.iss.one/ArtificialIntelligenceArticles

Our CVPR'19 paper about neural free-viewpoint rendering of human avatars without reconstructing geometry is on arXiv! Generator predicts UV mapping (not RGB), and texture is learned per-avatar.

🌐 (link: https://saic-violet.github.io/texturedavatar) saic-violet.github.io/texturedavatar
▶️ (link: https://youtu.be/3rrnUX8wWZ8) youtu.be/3rrnUX8wWZ8
📝 (link: https://arxiv.org/abs/1905.08776) arxiv.org/abs/1905.08776

Speech2Face: Learning the Face Behind a Voice #CVPR2019



ArXiv
arxiv.org/abs/1905.09773
Project
speech2face.github.io

Image Alignment in Unseen Domains via Domain Deep Generalization. arxiv.org/abs/1905.12028

Incidence Networks for Geometric Deep Learning. arxiv.org/abs/1905.11460

KnowYourAI: Developing a Framework to Address Bias in Facial Expression Recognition
https://towardsdatascience.com/knowyourai-developing-a-framework-to-address-bias-in-facial-expression-recognition-b3b8040b0a68

Natural Language Processing and it's Applications
https://codecampanion.blogspot.com/2019/01/natural-language-processing-and-its.html

Flow-Based Generative Models, Bijective Transforms and Neural Lossless Compression
https://armenag.com/2019/05/30/flow-based-generative-models-bijective-transforms-and-neural-lossless-compression/

Five Functions of the Brain that are Inspiring #AI Research: https://towardsdatascience.com/five-functions-of-the-brain-that-are-inspiring-ai-research-2ba482ab8e2a
————
#BigData #MachineLearning #DataScience #Neuroscience #NeuralNetworks #Algorithms #DeepLearning

MRI Images Created by #AI Could Help Train #DeepLearning Models. https://healthitanalytics.com/news/mri-images-created-by-ai-could-help-train-deep-learning-models #BigData #Analytics #MachineLearning #DataScience #IoT #IIoT #Python #RStats #TensorFlow #JavaScript #ReactJS #VueJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #NeuroScience

Facebook #GHC19 Scholarship application is now open.
Deadline is Friday, June 29th, 5:00pm PDT.


https://www.facebook.com/careers/v2/jobs/2306282856126312/

Geometric Deep Learning making strides.
Videos available.


https://www.ipam.ucla.edu/programs/workshops/workshop-iv-deep-geometric-learning-of-big-data-and-applications/

A recent paper by Google AI researchers on scaling up CNNs in a more structured manner.
This was published in ICML 2019!

In general, the EfficientNet models achieve both higher accuracy and better efficiency over existing CNNs.

https://www.profillic.com/paper/arxiv:1905.11946

A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
Kohl et al.: https://arxiv.org/abs/1905.13077
#ArtificialIntelligence #DeepLearning #MachineLearning

Gaussian Differential Privacy
Dong et al.: https://arxiv.org/abs/1905.02383
#MachineLearning #Cryptography #Security #DataStructures #Algorithms

7 Tesla MRI of the ex vivo human brain at 100 micron resolution
Edlow et al.: https://www.biorxiv.org/content/biorxiv/early/2019/05/31/649822.full.pdf
#artificialintelligence #brain #human #technology