AI News, Alphabet's DeepMind Makes a Key Advance in Computer Vision

Alphabet's DeepMind Makes a Key Advance in Computer Vision

Researchers at Alphabet’s DeepMindtoday described amethodthat they say canconstruct a three-dimensional layoutfrom just a handful of two-dimensional snapshots.

The researchers give, as an example, a robot arm that can be abstracted as a simple articulation, with several joints, which is then constructed using data on form, color and so forth.

By manipulating the abstraction first and filling in details later, the system can work much faster thanrendering systems that attempt to manipulate huge sets of three-dimensionally related points.

In a video supplied by DeepMind, the neural nets classify these objects asone of two kinds: Either they are versions of a template that’s been rotated in one or more planesor they are mirror images of that template.The DeepMind networks do the job well.

It’s the human ability to do this sort of thing, as well as to figure out what must lie behind a barrier to vision—like a lock of hair or a branch of a tree—that explains why we can navigate complex environments so well.

A human being knows, from simple experience of the world, that a person who is in the sitting position is almost always to be found on a chair (and only very rarely on thin air, as circus mimes might do).

By Philip Ross Researchers at Alphabet’s DeepMind today described a method that they say can construct a three-dimensional layout from just a handful of two-dimensional snapshots.

And, the researchers write, it does the job by observation alone, without anyone having to first label the objects and “without any prior specification of the laws of perspective, occlusion, or lighting.” The researchers use two neural networks, a representation network and a generation network.

The researchers give, as an example, a robot arm that can be abstracted as a simple articulation, with several joints, which is then constructed using data on form, color and so forth.

By manipulating the abstraction first and filling in details later, the system can work much faster than rendering systems that attempt to manipulate huge sets of three-dimensionally related points.

In a video supplied by DeepMind, the neural nets classify these objects as one of two kinds: Either they are versions of a template that’s been rotated in one or more planes or they are mirror images of that template.

It’s the human ability to do this sort of thing, as well as to figure out what must lie behind a barrier to vision—like a lock of hair or a branch of a tree—that explains why we can navigate complex environments so well.

Axios

The context: Computer vision — spurred by the availability of data and increased computing power — has rapidly advanced in the past six years.

Many of the underlying algorithms largely learn via supervision: an algorithm is given a large dataset that is labeled with information (for example, about the object in a scene) and uses it to predict an output.

We need a step up in hardware capabilities and the techniques to build these deep neural networks and train them.” Go deeper: Read more about the various ways researchers are trying to design AI to work like the human brain.

MIT 6.S094: Deep Learning

This is lecture 1 of course 6.S094: Deep Learning for Self-Driving Cars (2018 version). This class is free and open to everyone. It is an introduction to the practice ...

Nick Bostrom: "Superintelligence" | Talks at Google

Superintelligence asks the questions: What happens when machines surpass humans in general intelligence? Will artificial agents save or destroy us?

Dr. Yann LeCun, "How Could Machines Learn as Efficiently as Animals and Humans?"

Brown Statistics, NESS Seminar and Charles K. Colver Lectureship Series Deep learning has caused revolutions in computer perception and natural language ...

It’s a little scary how smart Google’s DeepMind just got

It's a little scary how smart Google's DeepMind just got: Thanks for watching ..

Google I/O 2016 - Day 3 Track 1

Google Developer Days Europe 2017 - Day 2 (Auditorium)

Check in to the livestream to watch day 2 of GDD Europe '17! This livestream will cover all sessions taking place on the Auditorium stage of the ICE Congress ...

Lecture 2.3: Josh Tenenbaum - Computational Cognitive Science Part 3

MIT RES.9-003 Brains, Minds and Machines Summer Course, Summer 2015 View the complete course: Instructor: Josh ..

Livestream Day 2: Stage 6 (Google I/O '18)

This livestream covers all of the Google I/O 2018 day 2 sessions that take place on Stage 6. Stay tuned for technical sessions and deep dives into Google's latest ...

RL Course by David Silver Lecture 1 Introduction to Reinforcement Learning

Livestream Day 3: Amphitheater (Google I/O '18)

This livestream covers all of the Google I/O 2018 day 3 sessions that take place on the Amphitheater stage. Stay tuned for technical sessions and deep dives into ...