Name: Semi supervised learning, Variational Autoencoders and Deep NN and the brain
Start: 2020-11-01T18:00:00+02:00
End: 2020-11-01T19:00:00+02:00

Agenda:
18:00 - 18:05: Opening words
18:05 - 18:25: Semi supervised learning - Dror Parienta
18:25 - 18:45: Similarities between Artificial neural networks and the brain - Hadar Grimberg
18:45 - 19:05: Introduction to Variational AutoEncoders - Yehuda Katzav

-----------------------------------------------------------------------------------------------

Semi supervised learning - Dror Parienta
--------------------------------------------------------

Semi supervised learning refers to learning from data that includes only a few labeled examples together with a larger amount of unlabeled examples. The unlabeled data helps improve the performance of the model without the cost needed to obtain a fully labeled dataset.
In this talk we will present recent results from different approaches to semi supervised learning, including how to algorithmically tune weights for unlabeled data and how self supervised models are useful for Semi supervised image classification

Dror holds an M.Sc and B.Sc in Biotechnology Engineering from Ben-Gurion University, where he wrote his thesis on modeling the dynamics of exhaled respiratory droplets.

Similarities between Artificial neural networks and the brain - Hadar Grimberg
------------------------------------------------------------------------------
Are artificial neural networks tracing biological ones successfully?
Is it possible that deep neural networks can serve as a useful model to understand brain mechanism?
We will discuss similarities between the gross anatomy of the brain and deep network architectures, parallelization between learning modes and even characteristics like structural plasticity - the ability of the brain to modify its connections or rewire itself.

Hadar holds a Masters degree in Neuroscience from Haifa University.

Introduction to Variational AutoEncoders - Yehuda Katzav
-------------------------------------------------------------------------------
Variational AutoEncoders is a part of generative models family, basis on statistics and probability, What the construction of this model, How it work compare to other generative models, and why it's important to understand.

Yehuda holds a B.Sc in Applied Mathematics from Bar Ilan University, and interest in probabilistic models in the machine learning world.

Lea Polachek

Primrose Machine Learning Meetups

Technology

Artificial Intelligence

Machine Learning

Artificial Intelligence Applications

Machine Intelligence

Artificial Intelligence Programming

Machine Learning Interpretability

Deep Learning