Visual scenes are often comprised of sets of independent objects. Yet, current vision models make no assumptions about the nature of the pictures they look at.

Yannic Kilcher explore a paper on object-centric learning.

By imposing an objectness prior, this paper a module that is able to recognize permutation-invariant sets of objects from pixels in both supervised and unsupervised settings. It does so by introducing a slot attention module that combines an attention mechanism with dynamic routing.

Content index:

  • 0:00 – Intro & Overview
  • 1:40 – Problem Formulation
  • 4:30 – Slot Attention Architecture
  • 13:30 – Slot Attention Algorithm
  • 21:30 – Iterative Routing Visualization
  • 29:15 – Experiments
  • 36:20 – Inference Time Flexibility
  • 38:35 – Broader Impact Statement
  • 42:05 – Conclusion & Comments

Google recently released Quantization Aware Training (QAT) API, which enables developers to train and deploy models with the performance benefits of quantization — i.e., the process of mapping input values from a large set to output values in a smaller set — while retaining close to their original accuracy.

The goal is to support the development of smaller, faster, and more efficient machine learning models well-suited to run on off-the-shelf machines, such as those in medium- and small-business environments where computation resources are at a premium.

Here’s why that’s important:

Often, the process of going from a higher to lower precision tends to be noisy. That’s because quantization squeezes a small range of floating-point values into a fixed number of information buckets, leading to information loss similar to rounding errors when fractional values are represented as integers. (For example, all values in range [2.0, 2.3] might be represented in a single bucket.) Problematically, when the lossy numbers are used in several computations, the losses accumulate and need to be rescaled for the next computation.

Lex Fridman interviews David Silver for the Artificial Intelligence podcast..

David Silver leads the reinforcement learning research group at DeepMind and was lead researcher on AlphaGo, AlphaZero and co-lead on AlphaStar, and MuZero and lot of important work in reinforcement learning.

Time Index:

  • 0:00 – Introduction
  • 4:09 – First program
  • 11:11 – AlphaGo
  • 21:42 – Rule of the game of Go
  • 25:37 – Reinforcement learning: personal journey
  • 30:15 – What is reinforcement learning?
  • 43:51 – AlphaGo (continued)
  • 53:40 – Supervised learning and self play in AlphaGo
  • 1:06:12 – Lee Sedol retirement from Go play
  • 1:08:57 – Garry Kasparov
  • 1:14:10 – Alpha Zero and self play
  • 1:31:29 – Creativity in AlphaZero
  • 1:35:21 – AlphaZero applications
  • 1:37:59 – Reward functions
  • 1:40:51 – Meaning of life

One of the promising frontiers of research right now in chip design is using machine learning techniques to actually help with some of the tasks in the design process.

Here’s an interesting look at what Google is doing in this space.

We will be discussing this at our upcoming The Next AI Platform event in San Jose on March 10 with Elias Fallon, engineering director at Cadence Design Systems. (You can see the full agenda and register to attend at this link; we hope to see you there.) The use of machine learning in chip design was also one of the topics that Jeff Dean, a senior fellow in the Research Group at Google who has helped invent many of the hyperscaler’s key technologies, talked about in his keynote address at this week’s 2020 International Solid State Circuits Conference in San Francisco.

Lex Fridman inteviews Cristos Goodrow, VP of Engineering at Google and head of Search and Discovery at YouTube (aka YouTube Algorithm).

This conversation is part of the Artificial Intelligence podcast.

0:00 – Introduction
3:26 – Life-long trajectory through YouTube
7:30 – Discovering new ideas on YouTube
13:33 – Managing healthy conversation
23:02 – YouTube Algorithm
38:00 – Analyzing the content of video itself
44:38 – Clickbait thumbnails and titles
47:50 – Feeling like I’m helping the YouTube algorithm get smarter
50:14 – Personalization
51:44 – What does success look like for the algorithm?
54:32 – Effect of YouTube on society
57:24 – Creators
59:33 – Burnout
1:03:27 – YouTube algorithm: heuristics, machine learning, human behavior
1:08:36 – How to make a viral video?
1:10:27 – Veritasium: Why Are 96,000,000 Black Balls on This Reservoir?
1:13:20 – Making clips from long-form podcasts
1:18:07 – Moment-by-moment signal of viewer interest
1:20:04 – Why is video understanding such a difficult AI problem?
1:21:54 – Self-supervised learning on video
1:25:44 – What does YouTube look like 10, 20, 30 years from now?

Cruise, the self-driving subsidiary of General Motors, revealed its first vehicle to operate without a human driver, the Cruise Origin.

The vehicle, which lacks a steering wheel and pedals, is designed to be more spacious and passenger-friendly than typical self-driving cars.

Cruise says the electric vehicle will be deployed as part of a ride-hailing service, but declined to say when that might be.