

ML - The way the world works - analyzing how things work
David Nishimoto
Machine learning is the most important technological breakthrough in the 21st century. Listen to my views on the future of machine learning. Code demonstrations on YouTube under my channel David Nishimoto
Episodes
Mentioned books

Jul 30, 2020 • 19min
Robots unlimited
Human Face recognition differentiates unique physical attributes about a person face, the different heights, depths, and weights. Computer vision systems can pick peoples face out of a crowd almost instantaneously and measure various features of that face and compare the measurements with those faces stored in the database. Everyones face has distinguishable features for example peaks and troughs. There are about 80 of these features on the human face, including distance between the eyes, the width of the nose and the depth of the eye sockets. The computer after measuring the face creates a numerical number representing the face. Usually 14 to 22 of the 80 features in a face print is enough to complete the recognition process.

Jul 30, 2020 • 13min
Reinforcement learning nchain with open ai gym
Teaching a deep learning keras network how to play the nchain game

Jul 25, 2020 • 42min
Lstm
Strategies for lstm and keras and reinforced learning in business

Jul 19, 2020 • 18min
The business of software
Every software company should periodically reevaluate its products to determine if it is getting the breadth of offerings right. The danger is bundling weak products with strong ones and not improving them. “Horizontal markets can require enormous investment and skill to master.” “Once a company has crossed the chasm into the Early Majority with at least a niche product, it can be used as base to expand into other segments.” Look for related segments to leverage the technology expansion. Increasing sales force during the Early adopters is not preferred, because early adopters are not a strong reference source. The tipping point is 10 percent market acceptance.

Jul 18, 2020 • 21min
Consumer price index
The Consumer Price Index is sliced into the following percentages : 1% Tobacco , 3% Personal Care , 5% Apparel , 5% Medical Care , 6% Education , 6% Recreation , 16% Food and beverage , 18% Transportation , and 40% Housing .

Jul 18, 2020 • 42min
Keras and logistic regression and reinforcement learning as a pipeline
The idea for business

Jul 16, 2020 • 8min
Microturbines
Stirling engines are cost competitive with other small generator technologies, up to about 100 kW. The Stirling engine is externally heated, usually by combustion, to warm a gas that drives either pistons connected to a rotating power shaft or oscillating pistons that are supported by mechanical springs and gas bearings. Targeting the residential cogeneration market, many are packaging Stirlings as electric furnace or boiler replacements. Stirling cogeneration is popular in Europe.

Jul 16, 2020 • 18min
Logistic regression vs xgboost
Boston has become popular in kaggle competitions but is it better than logistic regression

Jul 15, 2020 • 17min
Logistisic regression to predict medical readmission
Predicting the likelihood of patient readmission saves money

Jul 11, 2020 • 37min
Becca the robot brain
An exploratory project to build a general purpose robot brain. https://e2eml.school/robot_brain_project.html


