The Neural Aesthetic is finished! Notes and around 30 hours of video lectures

The Neural Aesthetic @ ITP-NYU, Fall 2018

Gene Kogan

https://ml4a.github.io/classes/itp-F18/

An Introduction to Variational Autoencoders [93pp]


https://arxiv.org/abs/1906.02691v1

Is Optimization a Sufficient Language for Understanding Deep Learning?
https://www.offconvex.org/2019/06/03/trajectories/

iPython notebook for Attentive Neural Processes
https://arxiv.org/pdf/1901.05761.pdf

A special case are Neural Processes
https://arxiv.org/pdf/1807.01622.pdf

Try running the code on your browser (or phone) at:
https://colab.research.google.com/github/deepmind/neural-processes/blob/master/attentive_neural_process.ipynb

lecture notes from course on optimization for machine learning

Elad Hazan

https://drive.google.com/file/d/1GIDnw7T-NT4Do3eC0B5kYJlzwOs6nzIO/view

TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

Augustus Odena and Ian Goodfellow: https://arxiv.org/abs/1807.10875

Code: https://github.com/brain-research/tensorfuzz

#deeplearning #neuralnetworks #technology #innovation

Google TensorNetwork Library Dramatically Accelerates ML & Physics Tasks

https://medium.com/syncedreview/google-tensornetwork-library-dramatically-accelerates-ml-physics-tasks-8c7011e0f7b0

Here are the COMPLETE Lecture notes on Professor Andrew Ng's
Stanford Machine Learning Lecture: https://www.holehouse.org/mlclass/

Deep Learning Tools
PDF Version: https://drive.google.com/file/d/1XhngKISDpQgwGlvU-hjXWZb_qfyIYjqN/view

A curated list of decision, classification and regression tree research papers from the last 30 years with implementations. It covers NeurIPS, ICML, ICLR, KDD, ICDM, CIKM, AAAI etc.
https://github.com/benedekrozemberczki/awesome-decision-tree-papers

A key conference quality indicator is low paper acceptance rates. The CVPR 2019 paper acceptance rate dropped to 25.1 percent from last year’s 29.6 percent 🤓☝️

The list of all 1300 research papers accepted for CVPR 2019 is available here: https://openaccess.thecvf.com/CVPR2019.py

Given you spend 1 hour to read 1 article and the rate of 8 articles per day, it will take you about 6 months to read all of them. You'd better start right now 🙃

#CVPR2019 #computervision #patternrecognition #deeplearning #machinelearning

ICYMI: Prof. Strang wants to tell you about his newest course 18.065 "Matrix Methods in Data Analysis, Signal Processing, and Machine Learning." It's all free on OCW--->

https://ocw.mit.edu/courses/mathematics/18-065-matrix-methods-in-data-analysis-signal-processing-and-machine-learning-spring-2018/

Text2Scene: Generating Compositional Scenes from Textual Descriptions
Tan et al.: https://arxiv.org/abs/1809.01110
#ArtificialIntelligence #DeepLearning #MachineLearning

Tackling Climate Change with Machine Learning
Rolnick et al.: https://arxiv.org/abs/1906.05433
#artificialintelligence #climatechange #climatecrisis #machinelearning

Colab notebooks tutorials for Swift for TensorFlow
GitHub by Zaid Alyafeai: https://github.com/zaidalyafeai/Swift4TF
#artificialintelligence #machinelearning #swift #tensorflow

Efficient Exploration via State Marginal Matching
Lee et al.: https://arxiv.org/abs/1906.05274
#ArtificialIntelligence #Robotics #MachineLearning

Best research paper award at our Debugging ML workshop -- "Similarity of Neural Network Representations Revisited" by Geoffrey Hinton , Mohammad Norouzi, Honglak Lee, and Simon Kornblith
https://arxiv.org/abs/1905.00414
#ICLR2019 https://t.iss.one/ArtificialIntelligenceArticles

Visual Relationships as Functions: Enabling Few-Shot Scene Graph Prediction
Dornadula et al.: https://arxiv.org/pdf/1906.04876.pdf
#ArtificialIntelligence #DeepLearning #MachineLearning

new paper from Andrew Ng , Yoshua Bengio ,Demis Hassabis , .... arxiv.org/abs/1906.05433 https://t.iss.one/ArtificialIntelligenceArticles

Tackling Climate Change with Machine Learning

Collaboration between #CarnegieMellon Carnegie Mellon University School of Computer Science, University of Pennsylvania, ETH Zürich, University of Colorado Boulder, Element AI, Mila, Université de Montréal, Harvard University, Mercator Research Institute, Technische Universit¨at Berlin, Massachusetts Institute of Technology (MIT), Cornell University, Stanford University, DeepMind, GoogleAI, Microsoft Research arxiv.org/abs/1906.05433 https://t.iss.one/ArtificialIntelligenceArticles