[Virtual Community Meetup] December Lightning Talks

Lightning Talks are a series of virtual events featuring the PyTorch Lightning community. They are quick talks that give you insights on developments, projects and use cases the community is working on. We hope you get a bolt of inspiration! Agenda: Welcome by Eden Afek, Product Manager at PyTorch Lightning Talk #1 – “Sharded Model […]

#063 – Prof. YOSHUA BENGIO – GFlowNets, Consciousness & Causality

We are now sponsored by Weights and Biases! Please visit our sponsor link: http://wandb.me/MLST to get started creating a centralised, system of record for your team’s machine learning work. Patreon: https://www.patreon.com/mlst Discord: https://discord.gg/HNnAwSduud For Yoshua Bengio, GFlowNets are the most exciting thing on the horizon of Machine Learning today. He believes they can solve previously […]

#55 Self-Supervised Vision Models (Dr. Ishan Misra – FAIR).

Dr. Ishan Misra is a Research Scientist at Facebook AI Research where he works on Computer Vision and Machine Learning. His main research interest is reducing the need for human supervision, and indeed, human knowledge in visual learning systems. He finished his PhD at the Robotics Institute at Carnegie Mellon. He has done stints at […]

061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)

We are now sponsored by Weights and Biases! Please visit our sponsor link: http://wandb.me/MLST Yann LeCun thinks that it’s specious to say neural network models are interpolating because in high dimensions, everything is extrapolation. Recently Dr. Randall Bellestrerio, Dr. Jerome Pesente and prof. Yann LeCun released their paper learning in high dimensions always amounts to […]

2021's Biggest Advancements in Artificial Intelligence

2021 has been an incredible year in terms of advancements in the field of Artificial Intelligence Technologies. AI has managed to gain new abilities and managed to achieve the futuristic feat of taking over several jobs which previously only humans could perform. Whether it’s self-supervised learning, custom AI accelerators or neuromorphic chips, the future of […]

AI Enterprise Workflow Study Group – Course 4, Week 1

Hi Everyone, We’ve just completed Course 4: Machine Learning, Visual Recognition, and NLP, in the AI Enterprise Workflow Specialization study group. Course four was really interesting. Week 1 we reviewed model evaluation and performance metrics and week 2 we discussed building machine learning and deep learning models. Here’s a list of the topics covered in […]

CoRL 2020, Spotlight Talk 324: Multi-Modal Anomaly Detection for Unstructured and Uncertain Envir…

“**Multi-Modal Anomaly Detection for Unstructured and Uncertain Environments** Tianchen Ji (University of Illinois at Urbana-Champaign)*; Sri Theja Vuppala (University of Illinois at Urbana-Champaign); Girish Chowdhary (University of Illinois at Urbana Champaign); Katherine Driggs-Campbell (University of Illinois at Urbana-Champaign) Publication: http://corlconf.github.io/paper_324/ **Abstract** To achieve high-levels of autonomy, modern robots require the ability to detect and recover […]

CoRL 2020, Spotlight Talk 33: SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Ne…

“**SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks** Yan Xu (Chinese University of Hong Kong)*; Zhaoyang Huang (Zhejiang University); Kwan-Yee Lin (SenseTime Research); Xinge Zhu (The Chinese University of Hong Kong); Jianping Shi (Sensetime Group Limited); Hujun Bao (Zhejiang University); Guofeng Zhang (Zhejiang University); Hongsheng Li (Chinese University of Hong Kong) Publication: http://corlconf.github.io/paper_33/ **Abstract** […]

CoRL 2020, Spotlight Talk 426: ACNMP: Skill Transfer and Task Extrapolation through Learning from…

“**ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing** Mete Akbulut (Bogazici University)*; Erhan Oztop (Ozyeğin Üniversitesi); Muhammet Yunus Seker (Bogazici University); Hh X (University); Ahmet Tekden (Boğaziçi Üniversitesi); Emre Ugur (Bogazici University) Publication: http://corlconf.github.io/paper_426/ **Abstract** To equip robots with dexterous skills, an effective approach is to first […]

CoRL 2020, Spotlight Talk 464: Self-Supervised 3D Keypoint Learning for Ego-Motion Estimation

“**Self-Supervised 3D Keypoint Learning for Ego-Motion Estimation** Jiexiong Tang (KTH Royal Institute of Technology)*; Rareș Ambruș (Toyota Research Institute); Vitor Guizilini (Toyota Research Institute); Sudeep Pillai (Toyota Research Institute); Hanme Kim (Toyota Research Institute); Patric Jensfelt (Royal Institute of Technology); Adrien Gaidon (Toyota Research Institute) Publication: http://corlconf.github.io/paper_464/ **Abstract** Detecting and matching robust viewpoint-invariant keypoints is […]
CoRL 2020, Spotlight Talk 465: Self-Supervised Learning of Scene-Graph Representations for Robotics

CoRL 2020, Spotlight Talk 465: Self-Supervised Learning of Scene-Graph Representations for Robotics

**Self-Supervised Learning of Scene-Graph Representations for Robotic Sequential Manipulation Planning** Son Nguyen (University Stuttgart)*; Ozgur Oguz (Uni. of Stuttgart & Max Planck Inst. for Intelligent Systems ); Valentin Hartmann (University of Stuttgart); Marc Toussaint (Technische Universität Berlin) Publication: http://corlconf.github.io/paper_465/ **Abstract** We present a self-supervised representation learning approach for visual reasoning and integrate it into a […]

Crash Course In Machine Learning Part 2 – What Is Supervised Learning

In part 2 of a crash course in machine learning, we get an overview of three big algorithms for supervised learning. Linear regression for calculating continuous variables Logistic regression and neural networks for calculating discrete outputs Learn how to turn deep reinforcement learning papers into code: Deep Q Learning: https://www.udemy.com/course/deep-q-learning-from-paper-to-code/?couponCode=DQN-OCT-21 Actor Critic Methods: https://www.udemy.com/course/actor-critic-methods-from-paper-to-code-with-pytorch/?couponCode=AC-OCT-21 Curiosity […]

Deep Learning Basics: Introduction and Overview

An introductory lecture for MIT course 6.S094 on the basics of deep learning including a few key ideas, subfields, and the big picture of why neural networks have inspired and energized an entire new generation of researchers. For more lecture videos on deep learning, reinforcement learning (RL), artificial intelligence (AI & AGI), and podcast conversations, […]

DeepMind x UCL | Deep Learning Lectures | 10/12 | Unsupervised Representation Learning

Unsupervised learning is one of the three major branches of machine learning (along with supervised learning and reinforcement learning). It is also arguably the least developed branch. Its goal is to find a parsimonious description of the input data by uncovering and exploiting its hidden structures. This is presumed to be more reminiscent of how […]

DeepMind x UCL | Deep Learning Lectures | 4/12 | Advanced Models for Computer Vision

Following on from the previous lecture, DeepMind Research Scientist Viorica Patraucean introduces classic computer vision tasks beyond image classification (object detection, semantic segmentation, optical flow estimation) and describes state of the art models for each, together with standard benchmarks. She discusses similar models for video processing for tasks like action recognition, tracking, and the associated […]

Finishing the Treehouse Python Track | 100 Days of Code 13

This week I finished the Treehouse Learn Python Track! I also started learning about semi-supervised learning with GANs. Links mentioned in the video: Follow my Learning Progress on Trello! – https://trello.com/b/tyHAvpcY How I’m Learning Deep Learning in 2017 – https://medium.com/@MrDBourke/how-im-learning-deep-learning-in-2017-part-1-632f4187ce4c Medium 100 Days of Code Series – https://medium.com/series/my-100-days-of-code-bf23b507fc77 Treehouse Python Track – https://teamtreehouse.com/tracks/learn-python Udacity Intro […]

GANS for Semi-Supervised Learning in Keras (7.4)

Generative Adversarial Networks (GANs) are not just for whimsical generation of computer images, such as faces. GANs can also be an effective means of dealing with semi-supervised learning, where only some of the data are labeled. This video introduces semi-supervised learning for Keras. Code for This Video: https://github.com/jeffheaton/t81_558_deep_learning/blob/master/t81_558_class_07_4_gan_semi_supervised.ipynb Course Homepage: https://sites.wustl.edu/jeffheaton/t81-558/ Follow Me/Subscribe: https://www.youtube.com/user/HeatonResearch https://github.com/jeffheaton […]

ICLR 2020: Yann LeCun and Energy-Based Models

This week Connor Shorten, Yannic Kilcher and Tim Scarfe reacted to Yann LeCun’s keynote speech at this year’s ICLR conference which just passed. ICLR is the number two ML conference and was completely open this year, with all the sessions publicly accessible via the internet. Yann spent most of his talk speaking about self-supervised learning, […]

Ishan Misra: Self-Supervised Deep Learning in Computer Vision | Lex Fridman Podcast #206

Ishan Misra is a research scientist at FAIR working on self-supervised visual learning. Please support this podcast by checking out our sponsors: – Onnit: https://lexfridman.com/onnit to get up to 10% off – The Information: https://theinformation.com/lex to get 75% off first month – Grammarly: https://grammarly.com/lex to get 20% off premium – Athletic Greens: https://athleticgreens.com/lex and use […]

Lecture 1 | Machine Learning (Stanford)

Lecture by Professor Andrew Ng for Machine Learning (CS 229) in the Stanford Computer Science department. Professor Ng provides an overview of the course in this introductory meeting. This course provides a broad introduction to machine learning and statistical pattern recognition. Topics include supervised learning, unsupervised learning, learning theory, reinforcement learning and adaptive control. Recent […]