ML Blog

Sculpting in time

Do one thing and do it well.
Every story has a beginning and an end.

DeepMind UCL Deep Learning Online Course 1 Summary

Introduction to Machine Learning and Artificial Intelligence

2-Minute Read

Intro to Machine Learning & AI course address

Course content:

  1. Solving intelligence
  2. Alpha Go & Alpha Zero
  3. Learning to play capture the flag
  4. Folding protein with AlphaFold
  5. Overview of lecture series

Regarding the understanding of intelligence, there is a formula mentioned in the course


The source of the formula is from the paper A Definition of Machine Intelligence


Alpha Go and Alpha Zero use reinforcement learning to train themselves. An untrained neural network plays with itself to determine processing and adjust for errors, and then adjusts its own parameters to win more rewards through constant self-play.

Related papers: [Science: A general reinforcement learning algorithm that masters chess, shogi and Go through self-play](https://science.



Deepmind uses Capture the Flag mode to train neural networks in a game with team incentives.

Capture the Flag: the emergence of complex cooperative agents


The last narrative is the Protein Folding AlphaFold project, where the neural network acquires the amino acid sequence of the protein and the model starts to predict the distance between individual The model starts to predict the distance between amino acid pairs and the bond lengths and bond angles of the chemical bonds between amino acids, and then scores the generated protein structure, and uses a gradient descent algorithm to optimize the prediction model parameters so as to finally obtain the most stable protein structure.




Recent Posts



不断的学习思考, 保持好奇心
Keep thinking, Stay curious
Always be sensitive to new things