Pytorch-Struct

Fast, general, and tested differentiable structured prediction in PyTorch. By Harvard NLP : https://lnkd.in/e2iGiNa

#PyTorch #DeepLearning #ArtificialIntelligence

✴️ @AI_Python_EN

Evaluating the Factual Consistency of Abstractive Text Summarization
https://lnkd.in/ewFMX8T

#ArtificialIntelligence #DeepLearning #NLP #NaturalLanguageProcessing

✴ @AI_Python_EN

PaperRobot: Incremental Draft Generation of Scientific Ideas
https://lnkd.in/exHGHjW

#ArtificialIntelligence #AI #MachineLearning #DeepLearning

❇ @AI_Python_EN

Look then Listen: Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following

http://bit.ly/2Pn3PR4

#DataScience #MachineLearning #ArtificialIntelligence

✴ @AI_Python_EN

Deep learning hits mathematical theorem proofs

#deeplearning #artificialintelligence

https://arxiv.org/abs/1910.11797

❇ @AI_Python_EN

ICCV 2019 Best Papers Announced

https://medium.com/syncedreview/iccv-2019-best-papers-announced-27a1a21311e1


✴️ @AI_Python_EN

PipeDream: A new approach to parallelize DNN training with pipelining

#DataScience #MachineLearning #ArtificialIntelligence

http://bit.ly/32YHygq

✴️ @AI_Python_EN

Variational Temporal Abstraction

Taesup Kim, Sungjin Ahn, Yoshua Bengio

https://arxiv.org/pdf/1910.00775.pdf

#ActiveLearning #ArtificialIntelligence #DeepLearning

✴️ @AI_Python_EN

Bayesian Deep Learning Benchmarks

GitHub, by the Oxford Applied and Theoretical Machine Learning group

https://github.com/OATML/bdl-benchmarks

#Bayesian #DeepLearning

✴️ @AI_Python_EN

Neural Density Estimation and Likelihood-free Inference

George Papamakarios

https://arxiv.org/pdf/1910.13233.pdf

#Bayesian #NeuralDensityEstimation #Inference

✴️ @AI_Python_EN

Credit Risk Analysis Using #MachineLearning and #DeepLearning Models

Lovely paper by Peter Martey Addo, Dominique Guegan and Bertrand Hassani

Code on #Github (it's in #R)

https://github.com/brainy749/CreditRiskPaper

✴️ @AI_Python_EN

Very interesting paper where they solved the three-body problem using deep neural networks in a tremendously more computationally efficient manner. While there is a lot of talk about current deep learning not leading towards human-like intelligence, one must think more deeply as to all the fantastic areas, applications, and fields that current deep learning can be game-changing right now and can lead to a new era of human-machine collaboration.
#deeplearning
#solvingproblems

https://arxiv.org/abs/1910.07291

✴️ @AI_Python_EN

Facebook: Pushing state-of-the-art in 3D content understanding

#DataScience #MachineLearning #ArtificialIntelligence

http://bit.ly/2JBaYK5

✴️ @AI_Python_EN

A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models

https://arxiv.org/abs/1910.13148

#MachineLearning #neurips, #NeurIPS2019

✴️ @AI_Python_EN

How 20th Century Fox uses ML to predict a movie audience
Google Cloud Blog
http://bit.ly/2N3I7SC

#AI #DeepLearning #MachineLearning #DataScience

✴️ @AI_Python_EN

categorical data analysis I've found very helpful:
- Generalized Linear Models and Extensions (Hardin and Hilbe)
- Categorical Data Analysis (Agresti)
- Analyzing Categorical Data (Simonoff)
- Regression Models for Categorical Dependent Variables (Long and Freese)
- Applied Logistic Regression (Hosmer and Lemeshow)
- Logistic Regression Models (Hilbe)
- Analysis of Ordinal Categorical Data (Agresti)
- Applied Ordinal Logistic Regression (Liu)
Surveys also collect data in the form of counts ("How many times have you...").
Analyzing count data with methods designed for continuous data is usually unwise, and here are a couple of excellent books on that topic:
- Modeling Count Data (Hilbe)
- Negative Binomial Regression (Hilbe)
There are numerous "machine learners" I have also used over the years but, in general, they tell us less about the Why, essential in consumer research. Though predictive analytics is not typically the purpose of consumer surveys, used competently, statistical methods are also highly competitive with machine learning in terms of predictive accuracy.

❇️ @AI_Python_EN