Countering Algorithm Threat: Using curated training data to counteract bias in machine learning

Machine learning algorithms are like children, we have to teach them right from wrong

An Aside:

https://slides.com/lizh/countering-algorithm-threat

Beginner-friendly resources are attached to many of these slides

My company is releasing a 🤖 to help you be a better technical mentor!

Wanna beta test? 

bit.ly/enkibot

When some datasets have cross-validation used on them to train or validate models, you must train these algorithms with a reinforcement learning phase to properly calibrate a bias, because learning models produced by cross-validation are simple to perturb offensively

Use Inverse Reinforcement Learning, show the model strong examples of good, and strong examples of bad, so that it develops a deep bias.

Technical Thesis:

What do I mean by "Bias"

The constant factor against which a weight is applied in order to trace the curve of a function for Artificial Neural Networks

Prejudice in favor of or against one thing, person, or group compared with another, usually in a way considered to be unfair.

I mean...

not...

Teach your kids right from wrong

Add an inverse reinforcement learning step after you train your model, to appropriately teach your ANN

Use this tool to detect overly homogeneous training data

Reward Mechanisms

Concrete Problems in AI Safety

#NotAllMetrics
(can be used as reward functions)

http://humanetech.com/app-ratings/

Content suggestion trains users as much as it is trained by them

Noam Chomsky's Manufacturing Content

The signals of the world do not average to the truth

Offensive Perturbation is what they thought rock music was up to

Raise your kids, teach them right from wrong

or they will only tell us what they think most of us want to hear.