"HSBC to open 50-person AI lab in Toronto"

https://www.theglobeandmail.com/business/article-hsbc-to-open-50-person-artificial-intelligence-lab-in-toronto/

Great article on image enhancing (without NN!!!!)
https://sites.google.com/view/handheld-super-res/

NLP researchers: help Facebook detect false news.

https://research.fb.com/programs/research-awards/proposals/the-online-safety-benchmark-request-for-proposals/

Google researchers developed a way to peer inside the minds of deep-learning systems, and the results are delightfully weird.

https://www.technologyreview.com/f/610439/making-sense-of-neural-networks-febrile-dreams/

Turning cortical activity into speech using deep learning.
Pretty cool.
Some ways to go but still pretty cool.

Is the speed of our speech limited by the mechanical constraints of our articulatory apparatus, or is it limited by the speed of our speech-generating cortex?
If it is the former, people with speech-production implants may, one day, be able to speak faster than non-equipped people.

https://www.sciencemag.org/news/2019/01/artificial-intelligence-turns-brain-activity-speech

A triple interview of Geoff, Yoshua and me in the June issue of Communication of the ACM.


https://cacm.acm.org/magazines/2019/6/236987-reaching-new-heights-with-artificial-neural-networks/fulltext

A Guide for Making Black Box Models Explainable

By Christoph Molnar: https://christophm.github.io/interpretable-ml-book/ …

#ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks

https://youtu.be/TMFcfT5ZWC8 Peter Norvig Google AI Microsoft Research

A birds-eye view of optimization algorithms

By Fabian Pedregosa: http://fa.bianp.net/teaching/2018/eecs227at/

#ArtificialIntelligence #NeuralNetworks

State of the art- Latest from Google AI: Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction.
paper: https://www.profillic.com/paper/arxiv:1904.11111

These guys show improvement over state-of-the-art monocular depth prediction methods!

AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
Qian et al.: https://arxiv.org/abs/1905.05879
Demo: https://auspicious3000.github.io/autovc-demo/
#ArtificialIntelligence #DeepLearning #MachineLearning

ArviZ: Exploratory analysis of Bayesian models
Includes functions for posterior analysis, sample diagnostics, model checking, and comparison: https://arviz-devs.github.io/arviz/
#ArtificialIntelligence #Bayesian #BayesianInference #MachineLearning #Python

Machine Learning Open Source of the Month (v.May 2019)
https://medium.mybridge.co/machine-learning-open-source-for-the-past-month-v-may-2019-bf4ff9b80b1b

Model optimization with new Tensorflow tool
https://medium.com/tensorflow/tensorflow-model-optimization-toolkit-pruning-api-42cac9157a6a

Deep Flow-Guided Video Inpainting
Xu et al.: https://nbei.github.io/video-inpainting.html
#AritifcialIntelligence #DeepLearning #MachineLearning

Understanding Neural Networks via Feature Visualization: A survey
Nguyen et al.: https://arxiv.org/pdf/1904.08939v1.pdf
#neuralnetworks #generatornetwork #generativemodels

Unsupervised Learning with Graph Neural Networks
By Thomas Kipf.
Slides : http://helper.ipam.ucla.edu/publications/glws4/glws4_15546.pdf
Recording: http://www.ipam.ucla.edu/programs/workshops/workshop-iv-deep-geometric-learning-of-big-data-and-applications/?tab=schedule
#deeplearning #neuralnetworks #unsupervisedlearning #technology

Distributed deep learning/machine learning tasks

https://github.com/cerndb/dist-keras
https://github.com/Azure/DistributedDeepLearning/
https://towardsdatascience.com/deep-learning-with-apache-spark-part-2-2a2938a36d35

https://aiwiz.com/introduction-to-a-version-control-system-git-and-github/

https://www.intel.ai/introducing-nauta/#gs.ecvu0o

AI was 94 percent accurate in screening for lung cancer on 6,716 CT scans, reports a new paper in Nature, and when pitted against six expert radiologists, when no prior scan was available, the deep learning model beat the doctors: It had fewer false positives and false negatives.
https://www.nytimes.com/2019/05/20/health/cancer-artificial-intelligence-ct-scans.html

Revisiting Graph Neural Networks: All We Have is Low-Pass Filters "Our results indicate that graph neural networks only perform low-pass filtering on feature vectors"


https://arxiv.org/abs/1905.09550