Seeing What a GAN Cannot Generate

Bau et al.: https://arxiv.org/abs/1910.11626

#ArtificialIntelligence #DeepLearning #GenerativeAdversarialNetworks

Integer Discrete Flows and Lossless Compression
Hoogeboom et al.: https://arxiv.org/abs/1905.07376
#Artificialintelligence #DeepLearning #MachineLearning

"Differentiable Convex Optimization Layers"
CVXPY creates powerful new PyTorch and TensorFlow layers
Agrawal et al.: https://locuslab.github.io/2019-10-28-cvxpylayers/
#PyTorch #TensorFlow #NeurIPS2019

Deep Fundamental Matrix Estimation
https://vladlen.info/publications/deep-fundamental-matrix-estimation/
Paper- Code

The future belongs to Artificial Intelligence. Read this empirical research from the MIT-IBM Watson AI Lab on how tasks are reorganizing between people and machines as a result of AI and new technologies.

The report analyzes 170 million online job postings 2010-2017.

Read https://mitibmwatsonailab.mit.edu/research/publications/paper/download/The-Future-of-Work-How-New-Technologies-Are-Transforming-Tasks.pdf

Research Associates in Federated and Adversarial Machine Learning at Imperial College London
The Resilient Information Systems Security Group (RISS) in the Department of Computing at Imperial College London is seeking a Research Assistant/Associate to work on EU funded Musketeer project. Musketeer aims to create a federated and privacy preserving machine learning data platform, that is interoperable, efficient and robust against internal and external threats. Led by IBM the project involves 11 academic and industrial partners from 7 countries and will validate its findings in two industrial scenarios in smart manufacturing and health care. Further details about the project can be found at: www.musketeer.eu

The main contribution of the RISS group to Musketeer project focuses on the investigation and development of federated machine learning algorithms robust against attacks at training and test time, including the investigation of new poisoning attack and defence strategies, as well as novel mechanisms to generate adversarial examples and mitigate their effects. The work also includes the analysis of scenarios where multiple malicious users collude to manipulate or degrade the performance of federated machine learning systems.

There will be opportunities to collaborate with other researchers and PhD students in the RISS group working on adversarial machine learning and other machine learning applications in the security domain.

To apply for this position, you will need to have a strong machine learning background with proven knowledge and track record in one or more of the following research areas and techniques:

Adversarial machine learning.
Robust machine learning.
Federated or distributed machine learning.
Deep learning.
Bayesian inference.
Research Assistant applicants will have a Master’s degree (or equivalent) in an area pertinent to the subject area, i.e., Computing or Engineering. Research Associate applicants will have a PhD degree (or equivalent) in an area pertinent to the subject area, i.e., Computing or Engineering.

You must have excellent verbal and written communication skills, enjoy working in collaboratively and be able to organise your own work with minimal supervision and prioritise work to meet deadlines. Preference will be given to applicants with a proven research record and publications in the relevant areas, including in prestigious machine learning and security journals and conferences.

The post is based in the Department of Computing at Imperial College London on the South Kensington Campus. The post holder will be required to travel occasionally to attend project meetings and to work collaboratively with the project partners.

*Candidates who have not yet been officially awarded their PhD will be appointed as Research Assistant within the salary range £35,477 - £38,566 per annum.

How to apply:

Please complete our online application by visiting https://www.imperial.ac.uk/jobs/ and search using vacancy reference number ENG00916.

Applications must include the following:

A full CV and list of publications
A 1 page statement outlining why you think you would be ideal for this post.
Research Assistant salary in the range: £35,477 to £38,566 per annum*

Research Associate salary in the range: £40,215 to £47,579 per annum

Full Time, Fixed Term appointment for to start ASAP until the 31/11/2021



Should you have any queries regarding the application process please contact Jamie Perrins via [email protected]

Informal Enquiries can be addressed to Professor Emil Lupu ([email protected])

Closing Date 1st December 2019

10 Machine Learning Methods that Every Data Scientist Should Know
https://towardsdatascience.com/10-machine-learning-methods-that-every-data-scientist-should-know-3cc96e0eeee9

There is updated version of CS224n which uses pyTorch instead of tf and other updated resources. CS224N: Natural Language Processing with Deep Learning | Winter 2019:
https://www.youtube.com/playlist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z

GPT-2: 1.5B Release
OpenAI : https://openai.com/blog/gpt-2-1-5b-release/
#ArtificialIntelligence #DeepLearning #MachineLearning

The human brain can rewire itself after a traumatic bodily injury, researchers report. Similar findings have been previously reported in animal studies, but this is one of the first studies where such a result has been documented in people.

https://news.missouri.edu/2019/talk-to-the-hand/

Do Deep Neural Networks ‘See’ Faces Like Brains Do?

https://medium.com/syncedreview/do-deep-neural-networks-see-faces-like-brains-do-dc3eef334d79

A deeper dive into UMAP theory
Andy Coenen, Adam Pearce : https://pair-code.github.io/understanding-umap/supplement.html
#ArtificialIntelligence #DeepLearning #MachineLearning

When Artificial Intelligence gets FUNNY with an ability to detect humour & predict LAUGHTER using multimodal language dataset, named UR-FUNNY.
It demonstrated the role of context & punchline in humour detection using TED Talk transcripts with laughter cues for humour analysis.

#EMNLP2019
Read: https://arxiv.org/pdf/1904.06618.pdf
GitHub: https://github.com/ROC-HCI/UR-FUNNY

Learning to Predict Without Looking Ahead: World Models Without Forward Prediction

Rather than hardcoding forward prediction, we try to get agents to *learn* that they need to predict the future.

Check out our #NeurIPS2019 paper!

https://learningtopredict.github.io
https://arxiv.org/abs/1910.13038