Smash Notes

Back to Dr Raia Hadsell - Artificial Intelligence researcher, with Raia Hadsell.

What Is Deep Reinforcement Learning

Deep reinforcement learning is when artificial neural networks are brought together. When it comes to deep reinforcement learning, it uses a neural network that can have millions of neurons that are adapted and changed based on the input and output of the networks, which creates an action in the world.

Transcript

Dr Raia Hadsell - Artificial Intelligence researcher ·

Pint of Science

More from this episode

  1. Who Is Dr. Raia HadsellDr. Raia Hadsell is a senior research scientist that's part of the world renowned artificial intelligence company, DeepMind.
  2. What Is DeepMind, and What's the Company's GoalAI was intended for any computer program meant to emulate the decision processes of a human. DeepMind was originally a startup company pre-2014.
  3. What Is Go, and How Does It Help With AI ResearchGo is an ancient, simple game that involves one or two players that put down black or white stones and capture territory. It’s popularly played in Korea.
  4. What Does AI Look Like When Watching It on a ScreenDr. Hadsell states, unfortunately, that it’s nowhere near exciting as in the movies.
  5. How Would an AI React in Minecraft's Creative ModeDr. Hadsell states that this would be a problem in the AI study.
  6. How Do You Program an AI to Produce Something That Is Pure CreativeIt’s difficult to do. There are algorithms that try to mimic curiosity.
  7. Is There a Connection Between Neural Networks and the Human BrainThe human brain and other nervous systems in the biological world are the only examples we have of artificial intelligence. Dr.
  8. Is There Any Potential Research That Focuses on Creating an AI Neural Network That Can Be Applied to the BrainThere has been a rise in research of seeing things that look and act like grid cells in the neural network and training, when trained in a particular way…
  9. What Areas Are We Seeing AI Applied in Our Normal LivesIt depends on how you define AI.
  10. Can Neural Networks Help Teach Students?Having a curated curriculum for each student could be really valuable since each student learns different. Dr.
  11. How Do Raia Hadsell's Colleagues Catch a False Win?On Pint of Science, Dr. Raia Hadsell says a central question is how individual AI agents solve tasks, which tricks they find, and which behaviors emerge.
  12. How Much of the Codes Are Shared With Others, and How Much Do You Keep to YourselfWhen writing code in Google, it's hard to not use a lot of Google tools that are proprietary. Dr.
  13. Are the Scientists Trying to Make Tools to Solve What Humans Can’t Solve or Replicate Human IntelligenceDr. Hadsell believes the former not the latter, that they are trying to develop AI as a general problem-solving approach.
  14. What’s a Challenge That AI Is Least Suited to AddressThe most challenging things are when humans are making decisions that are abstract, vague, and contain inconsistent information.
  15. What Is a Problem of Learning Across a Lifetime of ExperienceContinually learning, having the knowledge continue over time. It’s far away from what scientists can do with the neural networks.

People

More answers like this

Related episodes

Plays from this note through the rest of the episode.

Note

Weekly highlights

One letter a week.

The notes worth hearing, with the minute they were said.