Improve Learning Algorithms

✅ Goal:

Learn faster or more efficiently from less data.

✅ Measures of Effectiveness:

• Sample Efficiency: How many examples does it need to reach a certain level of performance?
• Time-to-Convergence: How quickly does the model improve during training?
• Generalization: Does it perform well on unseen tasks or datasets?
• Few-shot / Zero-shot Performance: Can it learn or perform tasks with very little or no new training?

✅ Improvement Looks Like:

After modifying its learning algorithm, the system can learn new tasks faster or with less data — and still perform well.

✅ Questions:

• General Question:
  • Are there terms for assisted training versus autonomous learning
• Regarding Sample Efficiency
  • What is an example?
  • Is an example like an iteration?
  • How is performance measured? I.E., if \(M\)is a performance measure, what is \(M\)?
• Regarding Time-to-Convergence
  • What does convergence mean? Say M_i and M_i+1 are successive performance measures. Are we looking for \(|M_{i+1} - M_i| < \epsilon\) for an appropriate value of \(\epsilon\)
• Regarding Generalization
  • How do Autonomous AI Agents measure how well they perform on unseen tasks or data sets?
  • How can an Autonomous AI Agent evaluate its ability to learn or perform new or unseen tasks or data sets
• Regarding Few-shot / Zero-shot Performance
  • What is the difference between “Generalization” and “Few-shot / Zero-shot Performance”