Make your pictures beautiful with a touch of machine learning magic.

# Category Archives: AI

# Why Momentum Really Works vs Gradient Descent

# In Math We Trust: Quantum Computing, AI and Blockchain – The Future of IT

In memory of Prof Zhang Shoucheng 张首晟教授 who passed away on 1 Dec 2018.

Key Points :

- Quantum Computing with “
**Angel Particle**” (no anti-particle) : [Analogy] Complex Number (a + i.b) , ‘Anti’ = Conjugate = a – i.b, ‘No anti’ = Real number = a - A. I. Natural Language Algorithm : “
**Word To Vector**” eg. King / Queen (frequently appear together) , etc. - Data Privacy and Big Data Analytics with A. I. :
**Homomorphic Encryption**, ie reveal data but not privacy. (eg. Millionaire Problem)

# How AI can save our humanity | Kai-Fu Lee

From current jobs:

To future jobs:

Lee Kai-Fu 李开复: Former Apple VP of AI, Microsoft VP, Google (China) Chairman. Currently the founder of a Technology Venture Company in Beijing.

# Build Neural Network in Python from scratch

# 几何与计算数学的关系 – 丘成桐

__Geometry and Computing Math__

– Prof ST Yau (Harvard University Tenured Professor, Fields Medalist 1982, Wolf Prize 2010)

AI must be supported by solid Math Theory for it to be fully further developed.

This statement truly reflects the bottle-neck faced by the AI 2.0 (Expert Systems) in the 1980s using a non-rigorous “Fuzzy Logic” Math.

Current AI 3.0 (Deep Learning) is using Calculus (Cauchy Gradient Descent) to compute, it is empirical and *sans* proven math theoretical support.

The new Math tools like Persistent Homology (持续同调论) , Comformal Geometry 共形几何, etc may be the answer for future AI 4.0.

**Keywords**:

1. 蒙日-安培方程 Mongo-Ampere Equation

2. 共形(保角) 映射 Comformal Mapping

3. 仿射几何 Affine Geometry

4. 持续同调论 Persistent Homology

5. 叶状结构 Foliation Structure

# Machine Learning is Fun! – Adam Geitgey – Medium

https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471

(中文) :

https://zhuanlan.zhihu.com/p/24339995

Unsupervised learning is the future **ML** **(Machine Learning)** – of which **AI** is a branch – with the latest algorithm **Deeplearning** showing only 5% of its potential (more yet to be invented).

Singapore has recently launched an AI program to educate 10,000 students & workers. (Partnership with Microsoft and IBM, a 3-hour free lesson).

The world’s 4 AI gurus :

- (UK/Canada) Prof Geoffrey Hinton (*) , the inventor of DeepLearning, and
- his post-doctorate associate (France) Prof Yann Lecun ,
- The ex-Google & ex-Baidu AI Chief Prof Andrew NG 吴恩达,
- The AlphaGo creator Demis Hassabis

**Note**:

Andrew and Demis both studied in Singapore secondary schools (NG in Raffles Institution) before pursuing university in Stanford and Cambridge, respectively.

Note (*) : Prof Geoffrey Hinton was involved in the 80s Expert Systems where rule-based knowledge engine was the AI (2.0) . This AI failed because of fixed rules knowledge base under “**supervised learning**” from human domain experts, who each differed from another in opinions, to give an un-biased “weights” (rule probabilities from 0 to 1). Prof Hinton continued the AI research by moving from UK to Canada, where he developed the Deeplearning algorithm with **unsupervised learning** from Big Data Training feed to calculate the “Costs” (ie deviations of AI result versus actual result, using Cauchy’s Calculus eg. “Gradient Descent”, etc).

https://tomcircle.wordpress.com/2018/01/20/ai-deeplearning-machine-learnung/