Brain-Like Machine Learning Algorithms Enabling Real-Time Learning


Monday, October 24, 2016 - 6:30pm - 8:30pm


eBay Main Street

eBay Campus Main Street Building
2025 Hamilton Ave
San Jose, CA 95125
Tsvi Achler, Founder, Optimizing Mind

Event Details



*** Bring ID (e.g. Driver's License) for eBay Security ***   
6:30 Doors Open, Food & Networking   
7:00 Presentation   
*** Please arrive by 7 PM due to Security ***
Event Details
It remains unclear how the brain can be computationally flexible (quickly learn, modify, and use new patterns as it encounters them from the environment), and recall (reason with or describe recognizable patterns from memory). Today’s machine learning algorithms are “feedforward” which appears to limit their capability for recall, symbolic reasoning, or analysis.
This talk presents a new machine learning algorithm that recognizes by performing optimization on the current pattern that is being recognized. This is NOT optimization to learn weights, instead optimization to perform recognition. Subsequently, only simple Hebbian-like relational learning of expectations is required during learning.
The weights are no longer “feedforward”. The learning is more flexible and can be much faster (>>100x) and scalable (more than both neural nets and k-NN) especially for big data. I will present use cases in machine learning and cognitive phenomena.
Here are two videos that will help give some background. This will be one of the demos: This longer video introduces the background from a neuroscience computation perspective: 

Speaker Bio

Tsvi Achler is the founder of startup Optimizing Mind whose goal is to provide the next generation of machine learning algorithms. Tsvi has multidisciplinary background on the neural mechanisms of recognition. He has done extensive work in theory and simulations, human cognitive experiments, animal neurophysiology experiments, and clinical training. He worked as computer science researcher at Los Alamos National Labs and IBM Research. Tsvi received his bachelor degrees from UC Berkeley in Electrical Engineering and Computer Science, and PhD /MD in Neuroscience from University of Illinois at Urbana-Champaign.


Please RSVP on Meetup to help estimate food. 

Event page provided by ACM