The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial
arxiv.org/abs/1905.12787

Path-Augmented Graph Transformer Network. arxiv.org/abs/1905.12712

Defending Against Neural Fake News.

Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable adversaries to generate neural fake news: targeted propaganda that closely mimics the style of real news.

read more: https://www.profillic.com/paper/arxiv:1905.12616

Papers with Code !

https://paperswithcode.com

#artificialintelligence #codes #deeplearning #machinelearning

MetroTwitter - What Twitter reveals about the differences between cities and the monoculture of the Bay Area

Researcher collected 96K bios + 180M tweets from Twitters users in 13 major cities and visualized the differences between these cities:

- How people describe themselves
- What they talk about
- Popular emojis
- Most unique city

Code and data are open-sourced.

Website: https://huyenchip.com/2019/05/28/metrotwitter.html
GitHub: https://github.com/chiphuyen/MetroTwitter

#openresearch

​​Neural network that turns sketches into realistic photo.

Paper is called «Semantic Image Synthesis with Spatially-Adaptive Normalization».

#CVPR19 oral paper on a new conditional normalization layer for semantic image synthesis #SPADE and its demo app #GauGAN

ArXiV: https://arxiv.org/abs/1903.07291
Website: https://nvlabs.github.io/SPADE/

#GAN #CV #DL

​​Website using Deep Learning to colorize pictures.

Link: https://colourise.sg/#colorize

#DL #CV #demo

Attentive Generative Adversarial Network for Raindrop Removal from A Single Image

Abstract : "Raindrops adhered to a glass window or camera lens can severely hamper the visibility of a background scene and degrade an image considerably. In this paper, we address the problem by visually removing raindrops, and thus transforming a raindrop degraded image into a clean one. The problem is intractable, since first the regions occluded by raindrops are not given. Second, the information about the background scene of the occluded regions is completely lost for most part. To resolve the problem, we apply an attentive generative network using adversarial training (...)."

Qian et al.: https://arxiv.org/pdf/1711.10098.pdf

#artificialintelligence #deeplearning #generativeadversarialnetwork

Artificial intelligence won’t revolutionize anything if hackers can mess with it.

https://www.technologyreview.com/s/613170/emtech-digital-dawn-song-adversarial-machine-learning/?utm_source=facebook&utm_medium=tr_social&utm_campaign=site_visitor.unpaid.engagement

Current machine-learning systems cannot generate their own optical illusions—at least not yet.

https://www.technologyreview.com/s/612261/neural-networks-dont-understand-what-optical-illusions-are/?utm_campaign=owned_social&utm_medium=social&utm_source=facebook.com

Collection of pretrained models for PyTorch
https://github.com/rwightman/pytorch-image-models

"Gauge Equivariant Convolutional Networks and the Icosahedral CNN
" pretty interesting way of thinking, i like that
https://arxiv.org/pdf/1902.04615.pdf

Model optimization with new Tensorflow tool
https://medium.com/tensorflow/tensorflow-model-optimization-toolkit-pruning-api-42cac9157a6a

Brain Network Mechanisms of General Intelligence
https://www.biorxiv.org/content/biorxiv/early/2019/06/03/657205.full.pdf

Randomly wired neural networks and state-of-the-art accuracy? Yes it works.
https://towardsdatascience.com/randomly-wired-neural-networks-and-state-of-the-art-accuracy-yes-it-works-9fb3cedc8059

Robustness beyond Security: Representation Learning
https://gradientscience.org/robust_reps/

Reprojection Losses: Deep Learning Surpassing Classical Geometry in Computer Vision?
https://alexgkendall.com/computer_vision/Reprojection_losses_geometry_computer_vision/

Python framework that facilitates the quick development of complex video analysis applications and other series-processing based applications in a multiprocessing environment.
https://github.com/videoflow/videoflow

Natural Language Inference with Deep Learning (NAACL 2019 Tutorial)

the slides for the 2019 NAACL tutorial on Natural Language Inference with Deep Learning
by Sam Bowman and Xiaodan Zhu.

https://nlitutorial.github.io/nli_tutorial.pdf

Robotic Psychology What Do We Know about Human-Robot Interaction and What Do We Still Need to Learn?
https://scholarspace.manoa.hawaii.edu/bitstream/10125/59633/0193.pdf