​​Uber AI Plug and Play Language Model (PPLM)

PPLM allows a user to flexibly plug in one or more simple attribute models representing the desired control objective into a large, unconditional language modeling (LM). The method has the key property that it uses the LM as is – no training or fine-tuning is required – which enables researchers to leverage best-in-class LMs even if they don't have the extensive hardware required to train them.

PPLM lets users combine small attribute models with an LM to steer its generation. Attribute models can be 100k times smaller than the LM and still be effective in steering it

PPLM algorithm entails three simple steps to generate a sample:
* given a partially generated sentence, compute log(p(x)) and log(p(a|x)) and the gradients of each with respect to the hidden representation of the underlying language model. These quantities are both available using an efficient forward and backward pass of both models;
* use the gradients to move the hidden representation of the language model a small step in the direction of increasing log(p(a|x)) and increasing log(p(x));
* sample the next word

more at paper: https://arxiv.org/abs/1912.02164

blogpost: https://eng.uber.com/pplm/
code: https://github.com/uber-research/PPLM
online demo: https://transformer.huggingface.co/model/pplm
@Machine_learn
#nlp #lm #languagemodeling #uber #pplm

Practical Computer Vision Applications Using Deep Learning with CNNs — Ahmed Fawzy Gad (en) 2018

@Machine_learn

YOLACT (You Only Look At CoefficienTs) - Real-time Instance Segmentation
Results are impressive, above 30 FPS on COCO test-dev

AI & Art
@Machine_learn
some artist use the large collections of #data & #ML #algorithms to create mesmerizing & dynamic #installations

watch the video —> https://youtu.be/I-EIVlHvHRM

Machine Learning and Security — C. Chio, D. Freeman (en) 2018
#book #ML
@Machine_learn

@Machine_learn


Learning to See Transparent Objects

ClearGrasp uses 3 neural networks: a network to estimate surface normals, one for occlusion boundaries (depth discontinuities), and one that masks transparent objects

Google research: https://ai.googleblog.com/2020/02/learning-to-see-transparent-objects.html

Code: https://github.com/Shreeyak/cleargrasp

Dataset: https://sites.google.com/view/transparent-objects

3D Shape Estimation of Transparent Objects for Manipulation: https://sites.google.com/view/cleargrasp

Reinforcement learning
#deeplearning #reinforcement
#python
@Machine_learn

GANILLA: Generative Adversarial Networks for Image to Illustration Translation.

Github: https://github.com/giddyyupp/ganilla

Dataset: https://github.com/giddyyupp/ganilla/blob/master/docs/datasets.md

Paper: https://arxiv.org/abs/2002.05638v1

Deep learning of dynamical attractors from time series measurements

Embed complex time series using autoencoders and a loss function based on penalizing false-nearest-neighbors.

Code: https://github.com/williamgilpin/fnn

Paper: https://arxiv.org/abs/2002.05909

Deep Reinforcement Learning with Guar Performance
#DL #book #RL
@Machine_learn

@Machine_learn
IBM Data Science and AI Programs Free for 30 Days

https://onlinecoursesgalore.com/ibm-data-science-ai-coursera/

Coursera: https://www.coursera.org/promo/ibmdscommunity?ranMID=40328&ranEAID

@Machine_learn

Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer

https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html

Code: https://colab.research.google.com/github/google-research/text-to-text-transfer-transformer/blob/master/notebooks/t5-trivia.ipynb

Github: https://github.com/google-research/text-to-text-transfer-transformer

https://www.kaggle.com/sudalairajkumar/novel-corona-virus-2019-dataset


#Corona_virus dataset

@Machine_learn


Graph ML Surveys

A good way to start in this domain is to read what people already have done.

Videos
* Learning on Non-Euclidean Domains
* Stanford Course CS 224w
@Machine_learn
GNN
* Graph Neural Networks: A Review of Methods and Applications 2018
* A Comprehensive Survey on Graph Neural Networks 2019
* A Gentle Introduction to Deep Learning for Graphs 2019
* Deep Learning on Graphs: A Survey 2018
* Relational inductive biases, deep learning, and graph networks 2018
* Geometric deep learning: going beyond Euclidean data 2016
* Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview 2019
@Machine_learn
Graph kernels
* A Survey on Graph Kernels 2019
* Graph Kernels: A Survey 2019
@Machine_learn
Adversarial Attacks
* Adversarial Attack and Defense on Graph Data: A Survey 2018
@Machine_learn
Representation Learning
* Learning Representations of Graph Data -- A Survey 2019
* Representation Learning on Graphs: Methods and Applications 2017
@Machine_learn