Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
awesome-ai-safety
A curated list of awesome AI safety papers, projects and communities.
https://github.com/hari-sikchi/awesome-ai-safety
Last synced: 4 days ago
JSON representation
-
Table of Contents
-
Websites
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- cs.utexas.edu/users/ai-lab
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- Deep Learning News
- https://ai-alignment.com/?gi=7c7707e4c512
- https://80000hours.org/articles/ai-safety-syllabus/
- https://humancompatible.ai/bibliography
- http://aisafety.stanford.edu/
- https://intelligence.org/research/#publications
- https://ai-alignment.com/?gi=7c7707e4c512
- https://vkrakovna.wordpress.com/
- https://forum.effectivealtruism.org/
- deeplearning.net
- deeplearning.stanford.edu
- ai-junkie.com
- eecs.umich.edu/ai
- www-aig.jpl.nasa.gov
- cgi.cse.unsw.edu.au/~aishare
- isi.edu/AI/isd.htm
- nrl.navy.mil/itd/aic
- stat.ucla.edu
- deeplearning.cs.toronto.edu
- jeffdonahue.com/lrcn/
- Guide to Machine Learning
- https://ai-alignment.com/?gi=7c7707e4c512
- cs.brown.edu/research/ai
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- https://ai-alignment.com/?gi=7c7707e4c512
- aiai.ed.ac.uk
-
Videos and Lectures
- A beginners Guide to Deep Neural Networks
- Concrete problems in AI safety
- Safe Reinforcement Learning
- Safe RL robotics
- Concrete problems in AI safety
- Online course on AI safety
- Safe Reinforcement Learning
- Safe Reinforcement Learning
- Safe RL robotics
- Safe Artificial Intelligence
- Making Sense of the World with Deep Learning
- Demystifying Unsupervised Feature Learning
- Visual Perception with Deep Learning
- The Next Generation of Neural Networks
- Unsupervised Deep Learning - Stanford
- Natural Language Processing
- Deep Learning: Intelligence from Big Data
- Introduction to Artificial Neural Networks and Deep Learning
- NIPS 2016 lecture and workshop videos - NIPS 2016
- Machine Learning Discussion Group - Deep Learning w/ Stanford AI Lab
-
Tutorials
- The Best Machine Learning Tutorials On The Web
- UFLDL Tutorial 1
- UFLDL Tutorial 2
- Deep Learning for NLP (without Magic)
- Deep Learning from the Bottom up
- Theano Tutorial
- Neural Networks for Matlab
- Torch7 Tutorials
- Deep Learning with Python
- Grokking Deep Learning
- Deep Learning for Search
- A Deep Learning Tutorial: From Perceptrons to Deep Networks
-
Researchers
- Pascal Vincent
- Pedro Domingos
- Andrew W. Senior
- Brian Kingsbury
- Abdel-rahman Mohamed
- Adam Coates
- Alex Krizhevsky
- Alexander Ilin
- Andrej Karpathy
- Andrew M. Saxe
- Andrew Ng
- Andriy Mnih
- Ayse Naz Erkan
- Benjamin Schrauwen
- Bernardete Ribeiro
- Bo David Chen
- Boureau Y-Lan
- Dan Claudiu Cireșan
- Derek Rose
- Drausin Wulsin
- Erik M. Schmidt
- Galen Andrew
- Geoffrey Hinton
- George Dahl
- Graham Taylor
- Grégoire Montavon
- Hélène Paugam-Moisy
- Honglak Lee
- Hugo Larochelle
- Ilya Sutskever
- Itamar Arel
- James Martens
- Jason Morton
- Jason Weston
- Jeff Dean
- Jiquan Mgiam
- Joseph Turian
- Koray Kavukcuoglu
- KyungHyun Cho
- Ludovic Arnold
- Marc'Aurelio Ranzato
- Misha Denil
- Mohammad Norouzi
- Navdeep Jaitly
- Nitish Srivastava
- Noel Lopes
- Oriol Vinyals
- Patrick Nguyen
- Pierre Sermanet
- Quoc V. Le
- Reinhold Scherer
- Robert Coop
- Robert Gens
- Stéphane Mallat
- Tapani Raiko
- Tijmen Tieleman
- Tom Karnowski
- Ueli Meier
- Volodymyr Mnih
- Yann LeCun
- Yichuan Tang
- Yoshua Bengio
- Yotaro Kubo
- Ian Goodfellow
- Martin Längkvist
- Jürgen Schmidhuber
- Piotr Mirowski
- Roger Grosse
- Fei-Fei Li
-
Datasets
- Image Analysis Laboratory
- LIMSI-CNRS/CHM/IMM/vision
- NLM HyperDoc Visible Human Project - Color, CAT and MRI image samples - over 30 images (Formats: jpeg)
- The AR Face Database - Contains over 4,000 color images corresponding to 126 people's faces (70 men and 56 women). Frontal views with variations in facial expressions, illumination, and occlusions. (Formats: RAW (RGB 24-bit))
- UC Irvine Machine Learning Repository
- CMU PIE Database - A database of 41,368 face images of 68 people captured under 13 poses, 43 illuminations conditions, and with 4 different expressions.
- MNIST
- Google House Numbers
- CIFAR-10 and CIFAR-100
- Tiny Images
- Flickr Data
- Berkeley Segmentation Dataset 500
- Flickr 8k
- Flickr 30k
- Microsoft COCO
- Image QA
- AT&T Laboratories Cambridge face database
- AVHRR Pathfinder
- Amsterdam Library of Object Images - ALOI is a color image collection of one-thousand small objects, recorded for scientific purposes. In order to capture the sensory variation in object recordings, we systematically varied viewing angle, illumination angle, and illumination color for each object, and additionally captured wide-baseline stereo images. We recorded over a hundred images of each object, yielding a total of 110,250 images for the collection. (Formats: png)
- Annotated face, hand, cardiac & meat images - Most images & annotations are supplemented by various ASM/AAM analyses using the AAM-API. (Formats: bmp,asf)
- Image Analysis and Computer Graphics
- Brown University Stimuli - A variety of datasets including geons, objects, and "greebles". Good for testing recognition algorithms. (Formats: pict)
- CCITT Fax standard images - 8 images (Formats: gif)
- CMU VASC Image Database - Images, sequences, stereo pairs (thousands of images) (Formats: Sun Rasterimage)
- Caltech Image Database - about 20 images - mostly top-down views of small objects and toys. (Formats: GIF)
- Columbia-Utrecht Reflectance and Texture Database - Texture and reflectance measurements for over 60 samples of 3D texture, observed with over 200 different combinations of viewing and illumination directions. (Formats: bmp)
- Computational Colour Constancy Data - A dataset oriented towards computational color constancy, but useful for computer vision in general. It includes synthetic data, camera sensor data, and over 700 images. (Formats: tiff)
- Computational Vision Lab
- Densely Sampled View Spheres - Densely sampled view spheres - upper half of the view sphere of two toy objects with 2500 images each. (Formats: tiff)
- Digital Embryos - Digital embryos are novel objects which may be used to develop and test object recognition systems. They have an organic appearance. (Formats: various formats are available on request)
- Univerity of Minnesota Vision Lab
- FG-NET Facial Aging Database - Database contains 1002 face images showing subjects at different ages. (Formats: jpg)
- FVC2000 Fingerprint Databases - FVC2000 is the First International Competition for Fingerprint Verification Algorithms. Four fingerprint databases constitute the FVC2000 benchmark (3520 fingerprints in all).
- Biometric Systems Lab - University of Bologna
- German Fingerspelling Database - The database contains 35 gestures and consists of 1400 image sequences that contain gestures of 20 different persons recorded under non-uniform daylight lighting conditions. (Formats: mpg,jpg)
- Language Processing and Pattern Recognition
- Groningen Natural Image Database - 4000+ 1536x1024 (16 bit) calibrated outdoor images (Formats: homebrew)
- ICG Testhouse sequence - 2 turntable sequences from ifferent viewing heights, 36 images each, resolution 1000x750, color (Formats: PPM)
- IEN Image Library - 1000+ images, mostly outdoor sequences (Formats: raw, ppm)
- INRIA's Syntim images database - 15 color image of simple objects (Formats: gif)
- INRIA's Syntim stereo databases - 34 calibrated color stereo pairs (Formats: gif)
- Image Analysis Laboratory - Images obtained from a variety of imaging modalities -- raw CFA images, range images and a host of "medical images". (Formats: homebrew)
- Image Database - An image database including some textures
- JAFFE Facial Expression Image Database - The JAFFE database consists of 213 images of Japanese female subjects posing 6 basic facial expressions as well as a neutral pose. Ratings on emotion adjectives are also available, free of charge, for research purposes. (Formats: TIFF Grayscale images.)
- ATR Research, Kyoto, Japan
- MIT Vision Texture - Image archive (100+ images) (Formats: ppm)
- Machine Vision - Images from the textbook by Jain, Kasturi, Schunck (20+ images) (Formats: GIF TIFF)
- Mammography Image Databases - 100 or more images of mammograms with ground truth. Additional images available by request, and links to several other mammography databases are provided. (Formats: homebrew)
- Middlebury Stereo Data Sets with Ground Truth - Six multi-frame stereo data sets of scenes containing planar regions. Each data set contains 9 color images and subpixel-accuracy ground-truth data. (Formats: ppm)
- Middlebury Stereo Vision Research Page - Middlebury College
- Modis Airborne simulator, Gallery and data set - High Altitude Imagery from around the world for environmental modeling in support of NASA EOS program (Formats: JPG and HDF)
- National Design Repository - Over 55,000 3D CAD and solid models of (mostly) mechanical/machined engineerign designs. (Formats: gif,vrml,wrl,stp,sat)
- Geometric & Intelligent Computing Laboratory
- Otago Optical Flow Evaluation Sequences - Synthetic and real sequences with machine-readable ground truth optical flow fields, plus tools to generate ground truth for new sequences. (Formats: ppm,tif,homebrew)
- Photometric 3D Surface Texture Database - This is the first 3D texture database which provides both full real surface rotations and registered photometric stereo data (30 textures, 1680 images). (Formats: TIFF)
- SEQUENCES FOR OPTICAL FLOW ANALYSIS (SOFA) - 9 synthetic sequences designed for testing motion analysis applications, including full ground truth of motion and camera parameters. (Formats: gif)
- Computer Vision Group
- Stereo Images with Ground Truth Disparity and Occlusion - a small set of synthetic images of a hallway with varying amounts of noise added. Use these images to benchmark your stereo algorithm. (Formats: raw, viff (khoros), or tiff)
- Stuttgart Range Image Database - A collection of synthetic range images taken from high-resolution polygonal models available on the web (Formats: homebrew)
- The AR Face Database - Contains over 4,000 color images corresponding to 126 people's faces (70 men and 56 women). Frontal views with variations in facial expressions, illumination, and occlusions. (Formats: RAW (RGB 24-bit))
- The MIT-CSAIL Database of Objects and Scenes - Database for testing multiclass object detection and scene recognition algorithms. Over 72,000 images with 2873 annotated frames. More than 50 annotated object classes. (Formats: jpg)
- The RVL SPEC-DB (SPECularity DataBase) - A collection of over 300 real images of 100 objects taken under three different illuminaiton conditions (Diffuse/Ambient/Directed). -- Use these images to test algorithms for detecting and compensating specular highlights in color images. (Formats: TIFF )
- Robot Vision Laboratory
- The Xm2vts database - The XM2VTSDB contains four digital recordings of 295 people taken over a period of four months. This database contains both image and video data of faces.
- Centre for Vision, Speech and Signal Processing
- Traffic Image Sequences and 'Marbled Block' Sequence - thousands of frames of digitized traffic image sequences as well as the 'Marbled Block' sequence (grayscale images) (Formats: GIF)
- IAKS/KOGS
- U Oulu wood and knots database - Includes classifications - 1000+ color images (Formats: ppm)
- UCID - an Uncompressed Colour Image Database - a benchmark database for image retrieval with predefined ground truth. (Formats: tiff)
- UMass Vision Image Archive - Large image database with aerial, space, stereo, medical images and more. (Formats: homebrew)
- USF Range Image Data with Segmentation Ground Truth - 80 image sets (Formats: Sun rasterimage)
- University of Oulu Physics-based Face Database - contains color images of faces under different illuminants and camera calibration conditions as well as skin spectral reflectance measurements of each person.
- Machine Vision and Media Processing Unit
- University of Oulu Texture Database - Database of 320 surface textures, each captured under three illuminants, six spatial resolutions and nine rotation angles. A set of test suites is also provided so that texture segmentation, classification, and retrieval algorithms can be tested in a standard manner. (Formats: bmp, ras, xv)
- Machine Vision Group
- View Sphere Database - Images of 8 objects seen from many different view points. The view sphere is sampled using a geodesic with 172 images/sphere. Two sets for training and testing are available. (Formats: ppm)
- PRIMA, GRAVIR
- Wiry Object Recognition Database - Thousands of images of a cart, ladder, stool, bicycle, chairs, and cluttered scenes with ground truth labelings of edges and regions. (Formats: jpg)
- 3D Vision Group
- Yale Face Database - 165 images (15 individuals) with different lighting, expression, and occlusion configurations.
- Yale Face Database B - 5760 single light source images of 10 subjects each seen under 576 viewing conditions (9 poses x 64 illumination conditions). (Formats: PGM)
- Center for Computational Vision and Control
- YouTube-8M Dataset - YouTube-8M is a large-scale labeled video dataset that consists of 8 million YouTube video IDs and associated labels from a diverse vocabulary of 4800 visual entities.
- Visual Object Classes Challenge 2012 (VOC2012) - VOC2012 dataset containing 12k images with 20 annotated classes for object detection and segmentation.
- Large-scale Fashion (DeepFashion) Database - Contains over 800,000 diverse fashion images. Each image in this dataset is labeled with 50 categories, 1,000 descriptive attributes, bounding box and clothing landmarks
- Efficient Content-based Retrieval Group
- Department Image Understanding
-
Blogs
- Siraj Raval's Deep Learning tutorials
- RAISE blog
- Towards safe reinforcement learning
- Caffe DockerFile
- Torch7 Cheat sheet
- Misc from MIT's 'Machine Learning' course
- An efficient, batched LSTM.
- Emotion Recognition API Demo - Microsoft
- AlphaGo - A replication of DeepMind's 2016 Nature publication, "Mastering the game of Go with deep neural networks and tree search"
- Machine Learning is Fun!
-
Frameworks
-
Papers
- Scalable agent alignment via reward modeling: a research direction
- AGI safety literature review
- Concrete Problems in AI safety
- Preventing Side-effects in Gridworlds
- A Gym Gridworld Environment for the Treacherous Turn
- Preferences Implicit in the State of the World
- Conservative Agency via Attainable Utility Preservation
- Penalizing side effects using stepwise relative reachability
- Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning
- Incorrigibility in the CIRL Framework
- The Off-Switch Game.
- Corrigibility
- Learning the Preferences of Ignorant, Inconsistent Agents
- Cooperative inverse reinforcement learning
- Towards Interactive Inverse Reinforcement Learning
- Repeated Inverse Reinforcement Learning
- Should robots be obedient?
- Inverse Reward Design
- Learning Robust Rewards with Adversarial Inverse Reinforcement Learning
- Simplifying Reward Design through Divide-and-Conquer
- An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
- Reward learning from human preferences and demonstrations in Atari
- Supervising strong learners by amplifying weak experts
- AI safety via debate
- Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
- Deep reinforcement learning from human preferences
- Agent-Agnostic Human-in-the-Loop Reinforcement Learning
- Avoiding Wireheading with Value Reinforcement Learning
- Reinforcement learning with a corrupted reward channel
- Safe Exploration in Finite Markov Decision Processes with Gaussian Processes
- Safe Exploration for Interactive Machine Learning
- Stagewise Safe Bayesian Optimization with Gaussian Processes
- Safe Exploration in Continuous Action Spaces
- A lyapunov based approach to safe Reinforcement Learning
- Lyapunov based safe policy optimization for continuous control
- IPO: Interior-point Policy Optimization under Constraints
- CPO: Constrained policy optimization
- Neural Turing Machines
- Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
- Mastering the Game of Go with Deep Neural Networks and Tree Search
- Batch Normalization
- Residual Learning
- MobileNets by Google
- Cross Audio-Visual Recognition in the Wild Using Deep Learning
- Dynamic Routing Between Capsules
- Matrix Capsules With Em Routing
- Efficient BackProp - ->
- Berkeley AI Research (BAIR) Laboratory
-
Conferences
-
Tools
- Visual Studio Tools for AI - Develop, debug and deploy deep learning and AI solutions -->
-
Programming Languages
Categories