Yann lecun

Very impressive speed-up of physics simulations using ConvNets emulators obtained through architecture search.
Results on 10 applications in climate modeling, plasma, etc.

https://arxiv.org/abs/2001.08055

How to implement a YOLO (v3) object detector from scratch in PyTorch: Part 1
Blog by Ayoosh Kathuria: https://blog.paperspace.com/how-to-implement-a-yolo-object-detector-in-pytorch/
#ArtificialIntelligence #ComputerVision #DeepLearning #MachineLearning #PatternRecognition

Capsules with Inverted Dot-Product Attention Routing

New routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent’s state and the child’s vote.

Code: https://github.com/apple/ml-capsules-inverted-attention-routing

Paper: https://openreview.net/pdf?id=HJe6uANtwH

Deep Learning

https://www.youtube.com/watch?v=6TB9CUB_RE4

Recurrent Neural Networks | MIT 6.S191


https://www.youtube.com/watch?v=SEnXr6v2ifU

join
https://t.iss.one/ArtificialIntelligenceArticles

Lecture by Vladimir Vapnik in January 2020, part of the MIT Deep Learning Lecture Series.
https://www.youtube.com/watch?v=Ow25mjFjSmg

Data used to train #AI can contain implicit racial, gender, or ideological biases. How can we champion processes to remove bias from AI?

https://www.anaconda.com/machine-learning-bias-fairness/

HypoML: Visual Analysis for Hypothesis-based Evaluation of Machine Learning Models. https://arxiv.org/abs/2002.05271

Reinforcement learning is one powerful paradigm for doing so, and it is relevant to an enormous range of tasks, including robotics, game playing, consumer modeling, and healthcare.
https://www.youtube.com/watch?v=FgzM3zpZ55o

2.7 million have enrolled in Andrew Ng’s Machine Learning course
- Geoffrey Hinton has been cited 340k times
- TensorFlow has been used in 60k OSS projects

Hypothesis: in 5 years, when these millions of students have gained hands-on experience, we'll have AI skills overflow.

some of the smartest people I know are leaving AI research for engineering/neuroscience. Their reasons?

1. We need to understand how humans learn to teach machines to learn.
2. Research should be hypothesis -> experiments, but AI research rn is experiments -> justifying results.

To learn how to design machine learning systems, I find it really helpful to read case studies to see how great teams deal with different deployment requirements and constraints. Here are some of my favorite case studies.

Topics covered: lifetime value, ML project workflow, feature engineering, model selection, prototyping, moving prototypes to production. It's completed with lessons learned and looking ahead!

https://medium.com/airbnb-engineering/using-machine-learning-to-predict-value-of-homes-on-airbnb-9272d3d4739d

Netflix streams to over 117M members worldwide, half of those living outside the US. The company uses machine learning to predict the network quality, detect device anomaly, handle predictive caching. https://netflixtechblog.com/using-machine-learning-to-improve-streaming-quality-at-netflix-9651263ef09f

This article explores the tradeoff between complexity and interpretability, performance and ease for production, for the classic task of fraud detection.

https://eng.lyft.com/from-shallow-to-deep-learning-in-fraud-9dafcbcef743

Most courses only teach you how to train your models. This is only one I've seen that shows you how to design, train, & deploy models. All videos are available. Great resource for those struggling with the ML system design Qs in interviews too. https://fullstackdeeplearning.com/march2019

Unsupervised Disentanglement of Pose, Appearance, and Background from Images and Videos

code https://github.com/NVIDIA/UnsupervisedLandmarkLearning

paper https://arxiv.org/pdf/2001.09518.pdf

A 2020 Guide to Deep Learning for Medical Imaging and the Healthcare Industry
https://nanonets.com/blog/deep-learning-for-medical-imaging/amp/

Monkeys Wake From Anaesthetic When Brain Region Linked to Consciousness Is Stimulated
https://www.cell.com/neuron/fulltext/S0896-6273(20)30005-2

These Lyrics Do Not Exist
Lyrics generated using Artificial Intelligence
Peter Ranieri: https://theselyricsdonotexist.com
#ArtificialIntelligence #Music #NeuralNetworks