Skip to main content

Understanding Aritificial Intelligence, Machine Learning and Deep Learning

 Table of Contents

1. Human Intelligence Vs Machine Learning and Artificial Intelligence

1.1 Example work from Jason Brown Lee

1.2. Building First neural network Model from Keras, Pytorch, Tensor Flow

2. Deep Learning

2.1 Unsupervised Learning no Human Intelligence

2.1 Human Face created or Synthesized Artificially

3. Web Resources 

3.1 Text Resources d2l, Jawson Lee, Michael Nielson

3.2 Video Resources from IISC, MIT, Standford, TED

 

1. Human Intelligence Vs Machine Learning and Artificial Intelligence

 Let us start with Diabetes Data, Here based on 8 blood/urine sample results, experienced doctor, classifies data as 1 or 0. Next year onset diabetes persons get '1' and no diabetes '0'. This data classification is purely done by Doctor for n-data-samples.


A neural network in Keras(Machine Learning Framework Python) is modeled, this samples are given as training and network model learns intelligence from Doctor. Later when we give new data sample, without Doctor intervention, our Network weights classifies the sampled as 1 or 0. Now, the Machine learned from training dataset and able to classify data is known as Artificial Intelligence or Machine Learning.

Pima Indians Diabetes Data 

 

2. Deep Learning

Machine learning is Human Supervised. Deep learning is Unsupervised learning.



 Image depth detection is the solution from Intel team for deep learning. They used Crowsourcing, MTurk amazon workers for this and six months of day and night GPU computation for their experiments.

Research Paper - IEEE

Deep Learning Neural Network Model at GitHub From Intel Team 

 Live Image Depth Detection

 

We did 4GL programming 1998, very vague Theories but 2020 all practical. 


3.0 Web Resources

3.1 Text Contents the best

Deep Dive in Learning

Resource describing nearly 27,000 more works of researchers all around the world with their papers and github source code lists.

Papers and Source code of Deep Learning 

3.2 Video Resources from IISC Summit 2017, MIT 2018, MIT 2020, Stanford, TED, etc.,

Youtube playlist containing top notch videos are placed in one place under Kathir Channel in the WorkWorship playlist.

Work Worship Playlist 


Summary

In this article  so far we covered Jawson Lee, Michael Nielson, Alexandar Amini, Lex Fridman,  Aashis Tendulkar, Fei Fei Li, Nitish Divakar works in the WebMap on Deep Learning.

 

 


Comments

Popular posts from this blog

All India - Kedarnath, Kasi Viswanath, Badrinath, Jagnath, Dhuvaraga, Amristar, Madurai, Kancheepuram, Tirumalai,

Kanyakumari - Kothaiyar Dam, Thiruparappu Falls, Mathur, Kulachekaram, Marthandam, Nagerkovil

Labour Intensive Versus Capital Intensive - Balance

  1. Labour intensive and Capital intensive, Economic policies two ways. Our policy is Mixed, ie., Labour and Capital. Ex. LIC, BHEL, SBI stands testimony to this. This Mixed economy is Unique for our Nation.   2. Adaptation New technology in any organisation, leads to Job Cut. Machine sucks human blood at the back and black side. Hindustan Teleprinters Ltd, Telecom service provider closed operation, since market dynamics changed from Dialed-Wired to Mobile. Nokia 2G enjoyed HTL closure. Years after same HTL closure happens to Nokia by the invention of " Touch Technology" and Korean SamSung Galaxy picked the Lion-Share of Market. 3. AI, Cloud, ML, 5G growth, we have to pay the heavy PRICE for adaptation to NEW INVENTIONS. Labours of HTL, Labours of Nokia not at the age group of 50's but 30's.   4. 5G RISKS    4. Any MNC, moving to 5G at the cost of Labours Job first. Thatz they claim as Optimized to $100 million is saving by moving to CLOUD. Black-side ...