ML - The way the world works - analyzing how things work

Latest Episodes:

Cog, Ghenhis, kismet and augment finite state machines Jun 10, 2020

Show notes

Ritchie says to Kismet, “I want to show you this watch my girlfriend gave me.” Kismet dutifully looks at the watch. Kismet was picking up on the social clues and the directions of attention. When Ritchie brought the watch into Kismets center of view, a few inches below his face where Kismet was foveated and when he brought his index finger up and tapped the watch the motion actived Kismets attention system and Kismet maintained eye contact with the watch. Eventually, Kismets attention system decided Ritchie’s face was more interesting and looked back at the eyes of Ritchie. There is nothing qualitatively different from the mechanism in Ghenhis.

Kshitij Bichave introduces beginners to reinforced learning Jun 09, 2020

Show notes

Learn how to get started in reinforced learning . Learn about the major breakthroughs in game playing and physics engines making reinforced learning interesting to use. Learn about reinforcement tools like open ai gym, or dota Rl coach, ray, rlkit, truffle

The shortage is not data, the shortage is logic on the edge Jun 06, 2020

Show notes

Machines could create logic and language on the edge

Honest Business Jun 03, 2020

Show notes

The complete idea: Several peopled involved in decision-making combined are not as powerful as a single vision. Accepting conventional solutions dilutes great ideas. Wo from covering up sin: "A completely honest and straight forward announcement to the public would have been more effective."

The feds bond buying reasons in the primary and secondary bond market and the affect on etfs May 31, 2020

Show notes

The announcement of the creation of the smccf caused corporate bond ETFs to line up with their NAVs. I provide a more detailed debate on the feds actions

Junk bonds May 30, 2020

Show notes

What could happen because of destabilization in the junk bond market

Mechanisms of the mind May 29, 2020

Show notes

The brain may not be as difficult to understand as previously thought. Instead, the problem may be it is too easy to understand.

Ryan Russon talks about human in the loop adding value through automation May 27, 2020

Show notes

We talk about learning from the past and making predictions in the future. It is more important to develop small developments that have fast return on investment than to build spocks brain https://www.meetup.com/Machine-Learning-Utah/ https://www.meetup.com/utah-data-engineering-meetup/ https://www.meetup.com/SLCPython/

Cnn networks and pooling and regularization and drop rate May 27, 2020

Show notes

Visualizing your network to understand why it work

Business process improvement May 25, 2020

Show notes

When an organization fails to make continuous simplification efforts a major portion of the managing process, it invites difficulty and poor performance; simplification is achieved by combining similar activities, reducing the amount of handling (reduce delays caused by handoffs and decision making), eliminating unused data and copies, and refining standard reporting.