SOTA results for Visual Exploration, CVPR-19 Habitat Challenge Winner, Sim-to-real, code, pretrained models and more!
Learning to Explore using Active Neural SLAM

Webpage:
https://devendrachaplot.github.io/projects/Neural-SLAM

Code:
https://github.com/devendrachaplot/Neural-SLAM


PDF:
https://arxiv.org/abs/2004.05155

❇️ @AI_Python_EN

Hello Learners,
Under affordable AI initiative, we are starting a new batch for Affordable Deep Learning And Advanced NLP batch. The time duration of the course will be for

link for registration
http://ineuron1.viewpage.co/Deep-learning-masters-with-NLP-and-computer-vision-krish-naik

5 months and 3 months of remote internship.
The course will be starting on April 18th, 2020.
he Live Online sessions will be held on Saturday and Sunday from 8 PM IST to 10 PM IST and Thursday 8 PM IST TO 10 PM IST for doubt clearing session

The course cost is 3000 INR + 18% GST for the whole course. All the sessions will be live online and it will be recorded. Please utilize this opportunity to upskill urself. Please check the below link for the syllabus and save your spot. The support team will call you for the registration. Happy Learning!!

Prerequisite is you need to know python. 60 hours of recorded videos will be available for python also.

❇️ @AI_Python_EN

Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks

CBC is a defense against adversarial examples. CBC lowering the computation and execution time compared with the similar available defenses.

Link:
https://arxiv.org/abs/2001.06099

❇️ @AI_Python_EN

A novel countermeasure against fault injection attacks for AES-based cryptosystems

Is a method for rousting AES and similar cryptography algorithm that uses SBOX against fault attacks.

https://ieeexplore.ieee.org/abstract/document/7585694

❇️ @AI_Python_EN

The very NeRF we all admire just got 9x faster!

https://github.com/krrish94/nerf-pytorch

Neural Radiance Fields (NeRF) paper to PyTorch
Try the (tiny-NeRF) Colab notebook at

https://colab.research.google.com/drive/1rO8xo0TemN67d4mTpakrKrLp03b9bgCX

abs: https://arxiv.org/abs/2003.08934

🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python

3D Photography using Context-aware Layered Depth Inpainting

github: https://github.com/vt-vl-lab/3d-photo-inpainting

project page: https://shihmengli.github.io/3D-Photo-Inpainting/

🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python

Transform and Tell: Entity-Aware News Image Captioning

End-to-end model which generates captions for images embedded in news articles.

Github: https://github.com/alasdairtran/transform-and-tell

Demo: https://transform-and-tell.ml/

Paper: https://arxiv.org/abs/2004.08070

🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python

BLEU might be Guilty but References are not Innocent - https://arxiv.org/abs/2004.06063 - We show that it is possible to calculate reliable automatic scores (even with BLEU) for high quality MT output by using a novel reference generation method.

Typical references exhibit poor diversity, concentrating around translationese language. Paraphrased references cover a wider diversity of target sentences and thus do not penalize alternative but equally accurate translations.

Releasing all reference translations gives the community a chance to revisit some of their decisions and measure quality differences for modeling techniques that produce more natural or fluent output which is penalized by standard references.

https://github.com/google/wmt19-paraphrased-references

🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python

work on COVID-19 detection from X-ray images by fine-tuning popular convolutional networks (such as ResNet, SqueezeNet, and DenseNet) here: https://arxiv.org/pdf/2004.09363.pdf

first re-labeled the publicly available COVID-19 images (collected by Joseph Paul Cohen PhD), with the help of a board-certified radiologist, and created COVID-Xray-5k dataset for binary classification of COVID-19 (we made this dataset publicly available via our Github).
We then trained multiple models on this dataset, and evaluated their sensitivity, specificity, ROC curve, AUC, and confusion matrix.

The PyTorch code for training and inference on our model are available here:
https://github.com/shervinmin/DeepCovid

Although the result looks promising, this is a first version of these models, and more experiments will be done once a larger dataset of cleanly labeled X-ray and CT images become available for COVID-19, for more concrete evaluation.

🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python

Free Read only access to e-journals backlist - content up to 2011

Free Read only access to the Brepols Complete e-book collection - content up to 2017

https://www-brepolsonline-net.proxy3.library.mcgill.ca/

Available until: 31-05-2020

Top 5 Github Repos to Learn Data Science/ AI (or copy some code!)


1. Awesome Data Science
By: Fatih Aktürk, Hüseyin Mert & Osman Ungur, Recep Erol.
https://lnkd.in/g9VRjip

2. data-scientist-roadmap
By: MrMimic
https://lnkd.in/gBRwKVw

3. Data Science Best Resources
By: Tirthajyoti Sarkar
https://lnkd.in/ghk3yBd

4. Ds-cheatsheets
By: Favio André Vázquez
https://lnkd.in/gJHjc5X

5. DataScienceResources
By: jb
https://lnkd.in/gfn6GxN

🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python

How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence

https://github.com/thunlp/LegalPapers

Paper:
https://arxiv.org/abs/2004.12158v2

Jukebox: a new generative model for audio from OpenAI.

Jukebox, a model that generates music with singing in the raw audio domain.

openai.com/blog/jukebox

Article: cdn.openai.com/papers/jukebox.pdf

Examples: https://jukebox.openai.com/

Code: https://github.com/openai/jukebox

Reinforcement Learning with Augmented Data

https://mishalaskin.github.io/rad

Code: https://github.com/MishaLaskin/rad

Paper: https://arxiv.org/abs/2004.14990

An NLU-Powered Tool to Explore COVID-19 Scientific Literature

https://ai.googleblog.com/2020/05/an-nlu-powered-tool-to-explore-covid-19.html

Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research

Awesome Sentiment Analysis papers: https://github.com/declare-lab/awesome-sentiment-analysis

Paper: https://arxiv.org/abs/2005.00357v1

Set of Machine Learning Python plugins for GIMP


Github: https://github.com/kritiksoman/GIMP-ML

Paper: https://arxiv.org/abs/2004.13060

Demo: https://www.youtube.com/watch?v=HVwISLRow_0

🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python

How to Create a Web API using Flask and Python

https://www.i2tutorials.com/how-to-create-a-web-api-using-flask-and-python/