#75 – Emergence [Special Edition] with Dr. DANIELE GRATTAROLA

Patreon: https://www.patreon.com/mlst Discord: https://discord.gg/ESrGqhf5CB Pod version: https://anchor.fm/machinelearningstreettalk/episodes/75—Emergence-Special-Edition-with-Dr–DANIELE-GRATTAROLA-e1hrb23 An emergent behaviour or emergent property can appear when a number of simple entities operate in an environment, forming more complex behaviours as a collective. If emergence happens over disparate size scales, then the reason is usually a causal relation across different scales. Weak emergence describes new properties […]

#69 DR. THOMAS LUX – Interpolation of Sparse High-Dimensional Data [UNPLUGGED]

Today we are speaking with Dr. Thomas Lux, a research scientist at Meta in Silicon Valley. In some sense, all of supervised machine learning can be framed through the lens of geometry. All training data exists as points in euclidean space, and we want to predict the value of a function at all those points. […]

Let's get physical – DeepMind: The Podcast (Season 2, Episode 4)

Do you need a body to have intelligence? And can one exist without the other? Hannah takes listeners behind the scenes of DeepMind’s robotics lab in London where she meets robots that are trying to independently learn new skills, and explores why physical intelligence is a necessary part of intelligence. Along the way, she finds […]

Speaking of intelligence – DeepMind: The Podcast (Season 2, Episode 2)

Hannah explores the potential of language models, the questions they raise, and if teaching a computer about language is enough to create artificial general intelligence (AGI). Beyond helping us communicate ideas, language plays a crucial role in memory, cooperation, and thinking – which is why AI researchers have long aimed to communicate with computers using […]

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 […]

SingularityNET: Modeling COVID-19 Using Simulated Agents with Intelligence and Culture – Dr. Deborah Duong

➡️ COVID-19 Simulation Summit Playlist: https://www.youtube.com/playlist?list=PLAJnaovHtaFR5puHCN4W_4o8cgIHdawDb ——————————————— 👀 About the speaker Dr. Deborah Duong is Director or AI Development at Rejuve and Director of Network Analytics at Singularity Net. The focus of her research is Complex Adaptive Systems, on the boundary between AI and Computational Social Science. She wrote the world’s first Intelligent Agent Based […]

SingularityNET: Panel: Simulating the Pandemic – Perspectives on COVID-19 modeling – COVID-19 Simulation Summit

➡️ COVID-19 Simulation Summit Playlist: https://www.youtube.com/playlist?list=PLAJnaovHtaFR5puHCN4W_4o8cgIHdawDb ——————————————— 👀 About the speakers Moderator: Gina Smith, PhD Based in Hong Kong, Gina Smith, PhD is the New York Times bestselling author of Apple cofounder Steve Wozniak’s biography, iWoz, and The Genomics Age, a 2008 Barron’s Book of the Year. A former ABC News correspondent and a longtime […]

CoRL 2020, Spotlight Talk 442: Hierarchical Robot Navigation in Novel Environments using Rough 2-…

“**Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps** Chengguang Xu (Northeastern University)*; Christopher Amato (Northeastern University); Lawson Wong (Northeastern University) Publication: http://corlconf.github.io/paper_442/ **Abstract** In robot navigation, generalizing quickly to unseen environments is essential. Hierarchical methods inspired by human navigation have been proposed, typically consisting of a high-level landmark proposer and a low-level controller. […]

CoRL 2020 Oral Session 6 – Perception

Chaired by: Abhinav Valada Paper Information: https://www.robot-learning.org/program#h.l0y1b1mqlwfo CoRL 2020: https://www.robot-learning.org YouTube Source for this Robot AI Video

Two Minute Papers: Virtual Reality Fluid Drawing Is Here! 🥛

❤️ Check out Weights & Biases and sign up for a free demo here: https://wandb.com/papers 📝 The paper “Interactive Liquid Splash Modeling by User Sketches” is available here: https://web.cse.ohio-state.edu/~wang.3602/Yan-2020-ILS/Yan-2020-ILS.pdf https://web.cse.ohio-state.edu/~wang.3602/publications.html 📝My earlier work on fluid control is available here: Real-time Control and Stopping of Fluids – Eurographics 2013, Poster – Károly Zsolnai, László Szirmay-Kalos (2013) […]

SingularityNET: COVID-19: A Front-Line Physician's Perspective – Ray & Roger Ng, MDs – COVID-19 Simulation Summit

➡️ COVID-19 Simulation Summit Playlist: https://www.youtube.com/playlist?list=PLAJnaovHtaFR5puHCN4W_4o8cgIHdawDb ——————————————— 👀 About the speakers Roger Ng, MD is cardiologist board certified in cardiovascular diseases and internal medicine passionate about bridging technology applications and AI for healthcare. He specializes in diagnostic imaging and treatment of congenital heart disease, valvular heart disease, coronary heart disease, heart failure, and arrhythmias. He […]

SingularityNET: Rejuve Live Demonstration – D.OS Event 2020

The Decentralized OS is an Online Summit gathering some of the most prestigious minds in blockchain, crypto, AI, finance and medicine. – Decentralized Health: The role of disruptive technologies, to support our fight against COVID-19 and create a better Healthcare Rejuve Technology has exclusive rights to develop therapies or diagnostics based on Network biodata. Revenue […]

SingularityNET: Infusing AGI with Compassion – PANEL 3 – AGI 2020 CONFERENCE

The AGI Society has organised its 13th Artificial General Intelligence Conference this year online. The AGI conference series is the only major conference series devoted wholly and specifically to the creation of AI systems possessing general intelligence at the human level and ultimately beyond. By gathering together active researchers in the field, for presentation of […]

CoRL 2020, Spotlight Talk 6: Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointc…

“**Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting** Xinshuo Weng (Carnegie Mellon University)*; Jianren Wang (Carnegie Mellon University); Sergey Levine (UC Berkeley); Kris Kitani (Carnegie Mellon University); Nicholas Rhinehart (UC Berkeley) Publication: http://corlconf.github.io/paper_6/ **Abstract** Many autonomous systems forecast aspects of the future in order to aid decision-making. For example, […]

SingularityNET: Agent-Based Modeling of Pandemics – Preliminary Results – Dr Ben Goertzel at D.OS 2020

SingularityNET and Singularity Studio have been gradually evolving our software framework for Agent-Based Modeling of the pandemic and leveraging it to run simulations of COVID-19 spread in various contexts. Watch as Dr Ben Goertzel describes some of the early results obtained in this quest. Learn more in this two-part blog series: https://bit.ly/ABMBlog1 https://bit.ly/ABMBlog2 —- SingularityNET […]

CoRL 2020, Spotlight Talk 476: Explicitly Encouraging Low Fractional Dimensional Trajectories Via…

“**Explicitly Encouraging Low Fractional Dimensional Trajectories Via Reinforcement Learning** Sean Gillen (UCSB)*; Katie Byl (UCSB) Publication: http://corlconf.github.io/paper_476/ **Abstract** A key limitation in using various modern methods of machine learning in developing feedback control policies is the lack of appropriate methodologies to analyze their long-term dynamics, in terms of making any sort of guarantees (even statistically) […]

SingularityNET: Decentralized Economy – NFTs and the Decentralization of Art

We are at the cusp of a paradigm shift. NFTs will revolutionize many industries, especially the creative industry/economy. By leveraging NFTs as a tool, it will now be possible to represent everything we see in our world in a digital form, doing so with a unique immutable identity attached to the blockchain. This will give […]

CoRL 2020, Spotlight Talk 389: Unsupervised Metric Relocalization Using Transform Consistency Loss

“**Unsupervised Metric Relocalization Using Transform Consistency Loss** Mike Kasper (University of Colorado)*; Fernando Nobre (Amazon); Christoffer Heckman (University of Colorado); Nima Keivan (Amazon) Publication: http://corlconf.github.io/paper_389/ **Abstract** Training networks to perform metric relocalization traditionally requires accurate image correspondences. In practice, these are obtained by restricting domain coverage, employing additional sensors, or capturing large multi-view datasets. We […]

CoRL 2020, Spotlight Talk 112: Iterative Semi-parametric Dynamics Model Learning For Autonomous R…

“**Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing** Ignat Georgiev (The University of Edinburgh)*; Christoforos Chatzikomis (Arrival); Timo Voelkl (Arrival); Joshua Smith (The University of Edinburgh); Michael Mistry (U of Edinburgh) Publication: http://corlconf.github.io/paper_112/ **Abstract** Accurately modeling robot dynamics is crucial to safe and efficient motion control. In this paper, we develop and apply an iterative […]

CoRL 2020, Spotlight Talk 452: Tolerance-Guided Policy Learning for Adaptable and Transferrable D…

“**Tolerance-Guided Policy Learning for Adaptable and Transferrable Delicate Industrial Insertion** Boshen Niu (Carnegie Mellon University); Chenxi Wang (Carnegie Mellon University); Changliu Liu (Carnegie Mellon University)* Publication: http://corlconf.github.io/paper_452/ **Abstract** Policy learning for delicate industrial insertion tasks (e.g., PC board assembly) is challenging. This paper considers two major problems: how to learn a diversified policy (instead of […]

CoRL 2020, Spotlight Talk 283: Learning Interactively to Resolve Ambiguity in Reference Frame Sel…

“**Learning Interactively to Resolve Ambiguity in Reference Frame Selection** Giovanni Franzese (Delft University of Technology)*; Carlos Celemin (TU Delft); Jens Kober (TU Delft) Publication: http://corlconf.github.io/paper_283/ **Abstract** In Learning from Demonstrations, ambiguities can lead to bad generalization of the learned policy. This paper proposes a framework called Learning Interactively to Resolve Ambiguity (LIRA), that recognizes ambiguous […]

CoRL 2020, Spotlight Talk 487: Attentional Separation-and-Aggregation Network for Self-supervised…

“**Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenes** Feng Gao (Tsinghua University)*; Jincheng Yu (Tsinghua University); Hao Shen (Meituan); Yu Wang (Tsinghua University); Huazhong Yang (Tsinghua University) Publication: http://corlconf.github.io/paper_487/ **Abstract** Learning depth and ego-motion from unlabeled videos via self-supervision from epipolar projection can improve the robustness and accuracy of the 3D perception and […]

CoRL 2020, Spotlight Talk 392: MultiPoint: Cross-spectral registration of thermal and optical aer…

“**MultiPoint: Cross-spectral registration of thermal and optical aerial imagery** Florian Achermann (ETH Zurich)*; Andrey Kolobov (Microsoft); Debadeepta Dey (Microsoft); Timo Hinzmann (ETH Zürich); Jen Jen Chung (ETH Zurich); Roland Siegwart (ETH Zürich, Autonomous Systems Lab); Nicholas Lawrance (ETH Zürich) Publication: http://corlconf.github.io/paper_392/ **Abstract** While optical cameras are ubiquitous in robotics, some robots can sense the world […]