Smash Notes
What Is a Problem of Learning Across a Lifetime of Experience
at 56:31
Answer
Continually learning, having the knowledge continue over time. It’s far away from what scientists can do with the neural networks. Learning from data set is different from how humans learn. It’s critical to learn in stages and to grow the knowledge and capability of the system to educate the AI to start with the small problems first.
Where this answer comes from
- Show
- Pint of Science
- Episode
- Dr Raia Hadsell - Artificial Intelligence researcher
- Date
People
More notes from this episode
- Who Is Dr. Raia Hadsell Transcript
- What Is DeepMind, and What's the Company's Goal Transcript
- What Is Go, and How Does It Help With AI Research Transcript
- What Does AI Look Like When Watching It on a Screen Transcript
- How Would an AI React in Minecraft's Creative Mode Transcript
- How Do You Program an AI to Produce Something That Is Pure Creative Transcript
- What Is Deep Reinforcement Learning Transcript
- Is There a Connection Between Neural Networks and the Human Brain Transcript
- Is There Any Potential Research That Focuses on Creating an AI Neural Network That Can Be Applied to the Brain Transcript
- What Areas Are We Seeing AI Applied in Our Normal Lives Transcript
- Can Neural Networks Help Teach Students? Transcript
- How Do Raia Hadsell's Colleagues Catch a False Win? Transcript
- How Much of the Codes Are Shared With Others, and How Much Do You Keep to Yourself Transcript
- Are the Scientists Trying to Make Tools to Solve What Humans Can’t Solve or Replicate Human Intelligence Transcript
- What’s a Challenge That AI Is Least Suited to Address Transcript
- What Is a Problem of Learning Across a Lifetime of Experience Transcript
More answers like this
- What’s a Challenge That AI Is Least Suited to Address
- Are the Scientists Trying to Make Tools to Solve What Humans Can’t Solve or Replicate Human Intelligence
- How Much of the Codes Are Shared With Others, and How Much Do You Keep to Yourself
- How Do Raia Hadsell's Colleagues Catch a False Win?
- What Is the Right Approach to Solve AI?
Related episodes
- Professor Sheena Cruickshank Immunologist & Microbiome Enthusiast
- UC Berkeley's Alison Gopnik: "Babies are the ultimate supercomputers"
- Why Silicon Valley Is Hiring Bird Experts
- How Can We Listen to 80 Years of Podcasts? Interview with Smashnotes founder Kirill Zubovsky
- David Silver and Lasse Espeholt of Ineffable Intelligence: A Superlearner for the Age of Experience
- ‘This Is Nuts.’ An OpenAI Insider Explains Why He Quit.
- Dylan Field: Is AI Replacing Designers?, Design is the New Code & Democratizing Creativity