home > research > 2018-machine-learning (2024-10-30)

Questions and Insights

Questions and Insights

Table of Contents

Machine Learning Questions

  • What are the factors in selecting new features
  • Selecting models
  • How does one test new features
  • How does one produce new features
  • How does one deploy new features
  • What is the process for regression
  • What visualization can be provided

http://www.scikit-yb.org/en/latest/tutorial.html https://docs.aws.amazon.com/machine-learning/latest/dg/ml-model-insights.html

https://aws.amazon.com/aml/faqs/

https://medium.freecodecamp.org/a-beginners-guide-to-training-and-deploying-machine-learning-models-using-python-48a313502e5a https://engineering.quora.com/Avoiding-Complexity-of-Machine-Learning-Systems

https://archive.ics.uci.edu/ml/datasets/Wine+Qualityhttps://archive.ics.uci.edu/ml/datasets/Wine+Quality

These are some of the areas we would want to consider (as well as areas that we don't want to consider):

Reading

https://www.nytimes.com/2018/10/18/business/q-and-a-yuval-harari.html https://www.nature.com/articles/d41586-018-07135-0

Nation States Sponsors

Current Uses

Reinforcement Learning: Text Prediction

https://skymind.ai/wiki/deep-reinforcement-learning#code https://skymind.ai/wiki/markov-chain-monte-carlo

This is effectively Markov chains with reward functions.

Reinforcement Learning: Example

https://becominghuman.ai/reinforcement-learning-step-by-step-17cde7dbc56c https://github.com/rfeinman/tictactoe-reinforcement-learning

  • Create Environment (agentstate, agentmove)
  • Create State
  • Specify reward
  • Create game.py https://inventwithpython.com/chapter10.html
  • Create agent.py
  • Create Actions list
  • Create game visualization
  • Create match visualizations

https://skymind.ai/wiki/deep-reinforcement-learning#code

This would also look at game boards.

https://github.com/topics/tic-tac-toe?l=javascript&o=desc&s=stars

Classification and Linear Regression

  • wines
  • flowers

Classification: Hotdog (Silicon Valley)

https://www.youtube.com/watch?v=ACmydtFDTGs

Classification: Cat or Dog

https://www.youtube.com/watch?v=cAICT4Al5Ow

Classification: Face detection

Classification: Facial Recognition

AdTech

https://www.spotx.tv/resources/blog/product-pulse/artificial-intelligence-vs-machine-learning-disrupting-ad-tech/ https://www.teads.tv/machine-learning-teads-4-use-cases-adtech-industry/

View-through rate prediction (VTR) Broken creative detection Bid-request relevancy prediction Look-alike Modeling (on-going)

FinTech

https://rubygarage.org/blog/machine-learning-in-fintechFraud prevention Risk management Investment predictions Customer service Digital assistants Marketing Network security Loan underwriting Algorithmic trading Process automation Document interpretation Content creation Trade settlements Money-laundering prevention Custom machine learning solutions

Generation: Horror Imagery

http://nightmare.mit.edu/

Generation: Painting Styles

https://www.instapainting.com/ai-painter-2

Generation: Image-to-image

https://github.com/phillipi/pix2pix

Generation: Colorizing Images

https://github.com/jantic/DeOldify

Training

Recommendations

Natural Language Processing (NLP)

Approaches

  • What is Supervised Learning?
  • What is Unsupervised Learning?
  • What is Reinforcement Learning?

MLaaS vs. Hosted

Machine Learning Use Cases

https://www.forbes.com/sites/bernardmarr/2016/09/30/what-are-the-top-10-use-cases-for-machine-learning-and-ai/#6754e8a894c9

Product Areas

https://machinelearningmastery.com/machine-learning-checklist/

  • predictive analytics
  • classification

Hiring and Skillsets

Focus on executives, designers, and business analysts.

Summarizing Entities

Creating Data Pipelines

https://papers.nips.cc/paper/5656-hidden-technical-debt-in-machine-learning-systems.pdf

Cleaning Data

Finding Features

https://www.infoworld.com/article/3259512/machine-learning/machine-learning-what-developers-and-business-analysts-need-to-know.html

Evaluating Features

Feature Importance and Correlated Features

https://www.youtube.com/watch?v=Q8rTrmqUQsU

Evaluating Models

Maintaining Models

DataLab and Experimentation

DataLab vs. Production

https://engineering.quora.com/Avoiding-Complexity-of-Machine-Learning-Systems

Outlier Management

Tracking Technical Debt

https://papers.nips.cc/paper/5656-hidden-technical-debt-in-machine-learning-systems.pdf

Design and Code Review

Documentation

Outliers   technical_debt

Monitoring Correlated Features

https://stats.stackexchange.com/questions/234668/how-should-i-deal-with-highly-correlated-features

Causation   technical_debt

Boundary Conditions   technical_debt

One sense in which all machine learning algorithms incur a technical debt is through the erosion of boundaries

https://www.kdnuggets.com/2015/01/high-cost-machine-learning-technical-debt.html

Monitoring Outcomes

Escalation

https://engineering.quora.com/Avoiding-Complexity-of-Machine-Learning-Systems

Scenarios

Author: Jason Walsh

j@wal.sh

Last Updated: 2024-10-30 16:43:54