Interview “The God Father of Deep Learning” Prof Geoffrey Hinton

Key Points:

  • Neural Network began in 70s.
  • AI in vogue in 80s, mainly Knowledge-based Expert System, inference engine only but NO self-learning capability.
  • “AI Winter” in 90s.
  • He could not get AI funding in UK.
  • Refused the USA military funding, he moved to Toronto University with Canadian funding on pure Basic AI research.
  • 4 decades of perseverence in Neural Network, he invented “DeepLearning” Algorithm using new approach (Machine ‘Self-learning’ capability by training in Big Data, learn from variance between output vs actual by using 19CE French mathematician Cauchy’s Calculus “Gradient Descent“. )
  • Hinton thanks Canada for Basic Research Funding.
  • Now working for Google.

Notes: The success of Hinton:

  1. Cross-discipline of 3 skills : (Psychiatrist + Math + IT) – Chinese proverb : 三个臭皮匠, 胜过一个诸葛亮 (3 ‘smelly’ cobblers beat the smartest military strategist Zhuge Liang in Chinese Three Kingdoms)
  2. Failures but with perseverence (4 decades)
  3. Courage (withstand loneliness) but with vision (see light at the end of tunnel)
  4. Look for condusive Research Environment : Canada Basic Research Funding
  5. Stick to his personal principle : Science for Peace of mankind, no ‘Military’ involvement.

[References] :

Gradient Descent in Neural Network (Video here) :

AI with Advanced Math helps in discovering new drugs

https://theconversation.com/i-build-mathematical-programs-that-could-discover-the-drugs-of-the-future-110689?from=timeline

Advanced Mathematical Methods with AI is a powerful tool:

  • Algebraic Topology (Persistent Homology)
  • Differential Geometry
  • Graph Theory

https://sinews.siam.org/Details-Page/mathematical-molecular-bioscience-and-biophysics-1

Math in Machine Learning

https://www.forbes.com/sites/quora/2019/02/15/do-you-need-to-be-good-at-math-to-excel-at-machine-learning/amp/

Certainly having a strong background in mathematics (eg. Linear Algebra, Multi-variables Calculus, Baeysian Probability, etc) will make it easier to understand machine learning at aconceptual level.

“If the math seems tough, focus on the practical first, learn through analogies and by building something yourself.

But if the math comes easy, you’re starting with a solid foundation.”