@machine_learn
A Survey on The Expressive Power of Graph Neural Networks

This is the best survey on the theory on GNNs I'm aware of. It produces so many illustrative examples on what GNN can and cannot distinguish.

It's funny, it's made by Ryoma Sato who I already saw from other works on GNNs and I thought it's one of these old Japanese professors with long beard and strict habits, but it turned out to be a 1st year MSc student 🇯🇵

Jason Brownlee
Machine Learning Mastery With Python
#book #python
@Machine_learn

"Deep learning for Computer Vision by Jason brownlee"

Please share it with me
@raminmousa
https://machinelearningmastery.com/deep-learning-for-computer-vision/

Clever Algorithms
#book #AI
@Machine_learn

​​
@Machine_learn
MaxUp: A Simple Way to Improve Generalization of Neural Network Training

A new approach to augmentation both images and text. The idea is to generate a set of augmented data with some random perturbations or transforms and minimize the maximum, or worst case loss over the augmented data. By doing so, the authors implicitly introduce a smoothness or robustness regularization against the random perturbations, and hence improve the generation performance. Testing MaxUp on a range of tasks, including image classification, language modeling, and adversarial certification, it is consistently outperforming the existing best baseline methods, without introducing substantial computational overhead.
.
.
.

paper: https://arxiv.org/abs/2002.09024

#augmentations #SOTA #ml

@Machine_learn

Paper:
https://arxiv.org/pdf/2003.05534.pdf

Github:
https://github.com/sniklaus/softmax-splatting

Short Summary:
https://www.marktechpost.com/2020/03/14/softmax-splatting-for-video-frame-interpolation/

Learning Pandas
#book #Python #Pandas
@Machine_learn

@Machine_learn


Fast and Easy Infinitely Wide Networks with Neural Tangents


https://ai.googleblog.com/2020/03/fast-and-easy-infinitely-wide-networks.html

Colab notebook: https://colab.research.google.com/github/google/neural-tangents/blob/master/notebooks/neural_tangents_cookbook.ipynb#scrollTo=Lt74vgCVNN2b

Code: https://github.com/google/neural-tangents

Paper: https://arxiv.org/abs/1912.02803

@Machine_learn

Meta-Transfer Learning for Zero-Shot Super-Resolution

Code: https://github.com/JWSoh/MZSR

Paper: https://arxiv.org/abs/2002.12213v1

A new paper from Samsung AI Center (Moscow) on unpaired image-to-image translation. Now – without any domain labels, even on training time!
▶️ youtu.be/DALQYKt-GJc
📝 arxiv.org/abs/2003.08791
📉 @Machine_learn

seaborn tutorial
#book #python @Machine_learn

@Machine_learn


Anomaly detection with Keras, TensorFlow, and Deep Learning

In this tutorial, you will learn how to perform anomaly and outlier detection using autoencoders, Keras, and TensorFlow.

https://www.pyimagesearch.com/2020/03/02/anomaly-detection-with-keras-tensorflow-and-deep-learning/

@Machine_learn

Graph Machine Learning research groups: Le Song

Le Song (~1981)
- Affiliation: Georgia Institute of Technology;
- Education: Ph.D. at U. of Sydney in 2008 (supervised by Alex Smola);
- h-index: 59;
- Awards: best papers at ICML, NeurIPS, AISTATS;
- Interests: generative and adversarial graph models, social network analysis, diffusion models.

@Machine_learn

Rethinking Image Mixture for Unsupervised Visual Representation Learning

Code: https://github.com/szq0214/Rethinking-Image-Mixture-for-Unsupervised-Learning

Paper: https://arxiv.org/abs/2003.05438v1

@Machine_learn

An AI program that plays Flappy Bird using reinforcement learning.


Code: https://github.com/taivu1998/FlapAI-Bird

Model: https://stanford-cs221.github.io/autumn2019-extra/posters/18.pdf

Paper: https://arxiv.org/abs/2003.09579

Gradient boost trees with xgboost and scikit-learn #book #python
@Machine_learn