How We Learn - A Book about Learning in Human Brain and Machines
From the book: How We Learn by Stanislas Dehaene

How We Learn - A Book about Learning in Human Brain and Machines

Recent developments in Machine Learning and Artificial Intelligence have ignited more interest and research on how humans learn. Recently I came across a book that compares human learning to how machines learn: 'How We Learn' by Professor Stanislas Dehaene. Overall it is an interesting book with intuitive explanations of how our brains work, how we learn at different stages of life and?how Machine Learning and neural networks mimics the biological learning process.

Here's a very brief summary of the key concepts in the book.?

The human brain is an extraordinary machine. Its ability to process information and adapt to circumstances by reprogramming itself is unparalleled, and it remains the best source of inspiration for recent developments in artificial intelligence.

Stanislas Dehaene starts the book by explaining that natural selection favored?the?emergence?of learning. He argues that genetic hardwiring helps.Humans possess some highly sophisticated learning algorithms that can refine those early skills according to our experience. Today, neural networks are not able to make the best use of data (therefore the need for massive or large foundation models). Compared to that a baby brain wins, hands-down.

Emerging theory is that our brain acts as a statistician, superior to machines. It was amusing to read that "even babies understand probabilities".?

Dehaene believes that neural networks mimic only a small part of our brain's function - the first few stages of sensory processing. This is where our brain operates in unconscious?matter (very fast) in the first 200-300 milliseconds.?

How We Learn by Stanislas Dehaene
How We Learn - Stanislas Dehaene


The book has three parts:

1 - What is learning - in silicon?and neural circuits - unconscious simulation - mental models - compare performance of computer algorithm vs brain - honing on theory of optimal learning, best learner operates as a scientist who makes rational use of probabilities and statistics

2 - How Our Brains learn - using psychology and neuroscience, the author explains why babies are the best learning machines! Nature and nurture join forces to help us learn.

3- The Four Pillars of Learning:

There are four universal pillars which massively modulate our ability to learn. These four pillars are:

a - Attention - a set o f neural circuits that select, amplify and propagate the signals that we view as relevant, multiplying their impact by x100. Note that attention is one of the key to success of transformer-based models like ChatGPT.

b - Active engagement - active generation of hypotheses with motivation and curiosity

c- Error Feedback - when world violates our expectations, error signals spread throughout our brain

d- Consolidation over time - brain compiles what it has acquired and transfers it into long-term memory, thus freeing neural resources for further learning. Repetition plays an essential role in this consolidation process. Sleep is not passive, brain revisits its past states at a faster pace and recodes the knowledge acquired during the day.?

Seven Definitions of Learning

This, I believe, is the unique value of this book. Here Stanislas Dehaene introduces the biological learning mechanisms and provides examples and explanations of Machine Learning techniques that correspond to each of these learning.

No alt text provided for this image
Neural Networks and Brain - How We Learn


He starts by a definition: Learning is to form an internal model of the external world. Then he presents seven ways to think learn.

Learning?is:

  1. adjusting the parameters of a mental model
  2. exploiting?a combinatorial explosion
  3. minimizing errors (he uses the example of a hunter adjusting telescope)
  4. exploring the space of possibilities
  5. optimising a reward function (backpropagation, actor/critic, adversarial learning)
  6. restricting search space
  7. projecting a prior hypotheses (its not nature vs nurture - how baby brain knows the difference between people and inanimate objects, via millions of years?of evolution)

I highly recommend reading the book for detailed explanations.

Overall I enjoyed reading the book and benefited from it. There is room for improvement though. There were a few stories in the book where I thought the author overplayed the capabilities of ML (for example, DeepMind playing games) and it would have been better to provide more information about its limits.

I hope that this summary was helpful and welcome any comments and thoughts on the fascinating topic of how to accelerate learning for humans or machines or even, together.

Nice summary, thanks for sharing! A recent lecture on YouTube of his proposes another important hypothesis, that of human singularity. Its really interesting given that his research encompasses subjects of different demography and cultures. https://www.youtube.com/watch?v=YxHLpb_urUk&t=564s

回复

Thanks Babar Bhatti just bought it!

回复
Aries Hilton

????????? ???????????????????? ??????????????; ?????????????????????? ???????????? & ???????????????????? ?????????????????? | ex-TikTok | Have A Lucid Dream? | All Views Are My Own. ??

2 年

If you like Psychology you'd love the Aries Hilton Storytelling Framework as it directly communicates with your subconscious https://www.dhirubhai.net/newsletters/7042928326218317825/

回复
Sajjad Ahmad

Professor at the University of Nevada Las Vegas (UNLV)

2 年

Great summary. Thanks

Johnnie Jones MSDA, MSEd

Researcher - Data Engineering - Gen AI - Business Intelligence - Advanced Analytics - Data Strategy, Data Governance, Data Protection and Data Architecture - MIT EMBA 2026 - MIT Sloan Student Senate

2 年

The authors of this book is a Cognitive Psychology - which is an area (cognitive science) that I’m studying now. Lots of interesting research has been done recently.

要查看或添加评论,请登录

Babar Bhatti的更多文章

  • My Notes on Co-Intelligence

    My Notes on Co-Intelligence

    I recently read the book Co-Intelligence by Ethan Mollick. My quick thoughts on it are in the clip below.

    2 条评论
  • Education and AI: Equity and Rights

    Education and AI: Equity and Rights

    I came across this interesting but lengthy discussion about AI and education at this page from Brookings Institute…

    1 条评论
  • Can AI be Contained?

    Can AI be Contained?

    Recently, I have been reading the history of technology especially how people from earlier times have dealt with major…

    6 条评论
  • Book Review: The Age of AI And Our Human Future

    Book Review: The Age of AI And Our Human Future

    Cover of the book: The Age of AI Here are a few thoughts and notes on a book that I recently read: "The Age of AI: And…

  • Executive Guide to ChatGPT

    Executive Guide to ChatGPT

    Within just a few days, the beta release of ChatGPT has demonstrated its potential - a conversational AI that can…

  • Pathways to Data Science and Machine Learning Roles

    Pathways to Data Science and Machine Learning Roles

    As the discussions around data and analytics get prevalent the activity in the world of data science and machine…

  • Understanding RNN and LSTM - Dallas AI Event Recap

    Understanding RNN and LSTM - Dallas AI Event Recap

    In our last event we covered one of the most interesting but least understood neural network architecture: recurrent…

  • 7 Success Factors for Enterprise AI Journey

    7 Success Factors for Enterprise AI Journey

    Leaders of organization which have recently started planning for their AI journey have a lot of challenges. Here are 7…

  • ML and Future of Self Driving Cars - Dallas AI April Event Recap

    ML and Future of Self Driving Cars - Dallas AI April Event Recap

    The world of self-driving cars has a lot going on. If you are not actively working in this field it is hard to keep…

    2 条评论
  • AI, Robotics and the New Age of Industrial Automation

    AI, Robotics and the New Age of Industrial Automation

    It was in 2016 that Klaus Schwab, founder of the World Economic Forum, made the "fourth industrial revolution" the…

社区洞察

其他会员也浏览了