State of the art video editing - make any object in a video invisible!

Deep Flow-Guided Video Inpainting
paper: https://www.profillic.com/paper/arxiv:1905.02884

Speech2Face: Learning the Face Behind a Voice.

By MIT CSAIL: https://arxiv.org/pdf/1905.09773.pdf

"The term “artificial intelligence” dates back to the mid-1950s, when mathematician John McCarthy, widely recognized as the father of AI, used it to describe machines that do things people might call intelligent. He and Marvin Minsky, whose work was just as influential in the AI field, organized the Dartmouth Summer Research Project on Artificial Intelligence in 1956. A few years later, with McCarthy on the faculty, MIT founded its Artificial Intelligence Project, later the AI Lab. It merged with the Laboratory for Computer Science (LCS) in 2003 and was renamed the Computer Science and Artificial Intelligence Laboratory, or CSAIL."


https://www.the-scientist.com/magazine-issue/artificial-intelligence-versus-neural-networks-65802

Limitations of Deep Learning for Vision, and How We Might Fix Them by Alan L. Yuille, Chenxi Liu: https://thegradient.pub/the-limitations-of-visual-deep-lea…/

The most serious challenge is how to develop algorithms that can deal with the combinatorial explosion as researchers address increasingly complex visual tasks in increasingly realistic conditions.

An Explicitly Relational Neural Network Architecture
Shanahan et al.: https://arxiv.org/abs/1905.10307
#deeplearning #neuralnetworks #symbolicAI

Learning to learn by Self-Critique
Antreas Antoniou and Amos Storkey: https://arxiv.org/abs/1905.10295
#ArtificialIntelligence #DeepLearning #MachineLearning

"A Latent Variational Framework for Stochastic Optimization"
By Philippe Casgrain: https://arxiv.org/abs/1905.01707
#ArtificialIntelligence #MachineLearning #Probability #Computation

Last week, Yann LeCun, Stanley Osher, René Vidal, Rebecca Willett and I organized the workshop "Deep Geometric Learning of Big Data and Applications" at Institute for Pure and Applied Mathematics, UCLA.

All talks, from theoretical to practical deep learning, were pretty inspiring. All videos are available here:
https://www.ipam.ucla.edu/programs/workshops/workshop-iv-deep-geometric-learning-of-big-data-and-applications/?tab=schedule

Thanks to all speakers, poster presenters, participants and IPAM for a wonderful and insightful week!

Aude Oliva (MIT): "there are about 200 papers using ConvNets to model the activity of the primate visual cortex."

She is running a challenge to explain fMRI and MEG data: https://algonauts.csail.mit.edu/challenge.html @ArtificialIntelligenceArticles

👁Computer Vision: Image Classification

https://www.adhiraiyan.org/deeplearning/computer-vision-image-classification

Yann Lecun : Ho parlato al quotidiano italiano La Stampa delle sfide che l'Intelligenza Artificiale sta affrontando oggi, dalle fake news ai contenuti inappropriati e di come insegnamo ai nostri sistemi a riconoscerli perchè possano intervenire e tutelarci.
Questa è senza dubbio una grande sfida ma ho fiducia nel futuro e negli sforzi che stiamo facendo per avvicinarci.

This is how I discussed with the italian daily La Stampa the key challenges AI is facing today, from fake news to inappropriate or extremist content, and how we teach our systems to understand those forms so that they can take an action to protect us.
It's a very challenging problem but I trust we'll get there, one day.

https://www.lastampa.it/2019/05/22/scienza/che-cosa-insegno-allia-yJ1jgYV5SH6nTbTOmfmmAN/

Good to watch
https://www.youtube.com/watch?v=Ioqrw4sCcwQ

Epileptic Seizure Classification ML Algorithms
https://towardsdatascience.com/seizure-classification-d0bb92d19962

Keras: Feature extraction on large datasets with Deep Learning
https://www.pyimagesearch.com/2019/05/27/keras-feature-extraction-on-large-datasets-with-deep-learning/

A curated list of gradient boosting research papers with implementations.

https://github.com/benedekrozemberczki/awesome-gradient-boosting-papers

Week 2 CS294-158 Deep Unsupervised Learning (2/6/19)

#UCBerkeley #deeplearning #computervision

https://m.youtube.com/watch?v=mYCLVPRy2nc&feature=share

ML algorithms and their math -
1. Naive Bayes - https://goo.gl/m3gh1o
2. Decision Trees (ID3) - https://goo.gl/HFqAd4
3. Random Forest - https://goo.gl/y3Au8M
4. K-means - https://goo.gl/worGWg
5. Ridge Regression - https://goo.gl/YGdUFr
6. Logistic Regression - https://goo.gl/zDvRcF

https://www.thelearningmachine.ai/ml

AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
Jeff Clune: https://arxiv.org/abs/1905.10985
#ArtificialIntelligence #ArtificialGeneralIntelligence #AGI

Understanding Hinton’s Capsule Networks. Part I: Intuition.
Blog by Max Pechyonkin: https://medium.com/ai³-theory-practice-business/understanding-hintons-capsule-networks-part-i-intuition-b4b559d1159b
#MachineLearning #DeepLearning #GeoffreyHinton #ArtificialIntelligence #Theory

"End-to-End Deep Reinforcement Learning without Reward Engineering"
They developed an end-to-end method that allows robots to learn from a modest number of images that depict successful completion of a task.

https://bair.berkeley.edu/blog/2019/05/28/end-to-end/