How AI and neuroscience drive each other forwards
https://www.nature.com/articles/d41586-019-02212-4

t-SNE algorithm on MNIST dataset in Kaggle kernels. NVIDIA's Rapids library with GPU acceleration. The algorithm achieves a 2000x speedup as compared to the sklearn version on CPU!
https://www.kaggle.com/tunguz/mnist-2d-t-sne-with-rapids

Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs. https://arxiv.org/abs/2002.02117

Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Varia... https://arxiv.org/abs/2002.02112

SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications
Hamdi et al.: https://arxiv.org/abs/1812.02132
Code https://github.com/ajhamdi/SADA
Video https://youtu.be/clguL24kVG0
#Cryptography #MachineLearning #Robotics

Nobel prize winner Danny Kahneman cited Gary Marcus (see the recent #AIdebate) and the need for hybrid models in science/AI (including reasoning and logic, in addition to learning), when referring to his systems 1 and 2 (see Thinking Fast and Slow). Neural-symbolic computing is a foundation for this line of research. #AAAI2020 congratulations to Francesca Rossi for the panel with Kahneman and the Turing Award winners. https://link.springer.com/book/10.1007/978-3-540-73246-4

PyTorch Wrapper version 1.1 is out!

New Features:

- Samplers for smart batching based on text length for faster training.

- Loss and Evaluation wrappers for token prediction tasks.

- New nn.modules for attention based models.

- Support for multi GPU training / evaluation / prediction.

- Verbose argument in system's methods.

- Examples using Transformer based models like BERT for text classification.

Check it out in the following links:

install with: pip install pytorch-wrapper

GitHub: https://github.com/jkoutsikakis/pytorch-wrapper

docs: https://pytorch-wrapper.readthedocs.io/en/latest/

examples: https://github.com/jkouts…/pytorch-wrapper/…/master/examples

#DeepLearning #PyTorch #NeuralNetworks #MachineLearning #DataScience #python #TensorFlow

Deep Learning: State of the Art (2020). Slides + video

Slides:
https://drive.google.com/file/d/10rZ4ldHUBoDu8bVoqGn-CEqGgX-w-oKm/view?usp=drivesdk

Video :
https://youtu.be/0VH1Lim8gL8

Image Fine-grained Inpainting
Hui et al.: https://arxiv.org/abs/2002.02609
Github: https://github.com/Zheng222/DMFN
#ArtificialIntelligence #DeepLearning #MachineLearning

Connections: Log Likelihood, Cross-Entropy, KL Divergence, Logistic Regression, and Neural Networks
https://towardsdatascience.com/connections-log-likelihood-cross-entropy-kl-divergence-logistic-regression-and-neural-networks-40043dfb6200

"If you really believe in an idea, never give up" - Geoff Hinton

#AAAI2020

An Introduction to Reinforcement Learning - Lex Fridman, MIT
Blog by Luke Kenworthy, RE•WORK : https://blog.re-work.co/an-introduction-to-reinforcement-learning-lex-fridman-mit/
#ReinforcementLearning #reworkAI #reworkDL

Continuous Geodesic Convolutions for Learning on 3D Shapes. https://arxiv.org/abs/2002.02506

The Future of Deep Learning Is Unsupervised, AI Pioneers Say
https://www.wsj.com/articles/the-future-of-deep-learning-is-unsupervised-ai-pioneers-say-11581330600

How to train a model with 10^11 parameters without running out of GPU memory?
Use DeepSpeed from Microsoft Research!
It's PyTorch compatible.
It partitions the network onto multiple processors automatically and efficiently.

https://www.microsoft.com/en-us/research/blog/zero-deepspeed-new-system-optimizations-enable-training-models-with-over-100-billion-parameters/

“It’s very much like the human body’s own immune system … [W]hen it finds something that doesn’t belong—that’s not self—it has an extremely precise and rapid response.”


https://www.technologyreview.com/s/612427/the-rare-form-of-machine-learning-that-can-spot-hackers-who-have-already-broken-in/

Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs
https://www.youtube.com/watch?v=IqkOZhfGEYs

TOP AI & ML RESEARCH TRENDS FOR 2020
https://www.topbots.com/top-ai-ml-research-trends-2020/

Who needs machine learning? Pigeons can be trained to classify medical images and diagnose heart disease https://pubmed.ncbi.nlm.nih.gov/31965462-taking-pigeons-to-heart-birds-proficiently-diagnose-human-cardiac-disease/