Available online at Medium. 

Online Deep Learning (ODL) and Hedge Back-propagation.
Apr 9, 2020
As the main concept of deep neural networks is to train through back-propagation in a batch setting, the data is required to be available in an offline setting. As a consequence, the scheme is irrelevant for many practical situations, in which the data arrives in sequence and cannot be stored. For example stocks, vehicle position, and many more. ODL is very challenging as it cannot use back-propagation. Two years ago, Sahoo et al (2018) addressed the gap between online learning and deep learning, where they claimed that “without the power of depth, it would be difficult to learn complex patterns”. They presented a novel framework for ODL.
An Overview of DeepSense Framework. 
Mar 12, 2020
I have found the DeepSense framework is one of the promising deep learning (DL) architectures for processing Time-Series sensing data in our artificial intelligence (AI) era. In this brief and intuitive overview, I’ll present the main ideas of the original paper titled “Deep Sense: A Unified DL Framework for Time-Series Mobile Sensing Data Processing” by Yao et-al. and can be found at www2017. The architecture from the original paper:
Karuch-Kuhn-Tucker (KKT) Conditions.
Aug 11, 2019. 
KKT conditions are first-order derivative tests (necessary conditions) for a solution to be an optimal. These conditions generalize the idea of Lagrange multipliers, where they allow to include not only equality constraint.


Algotrading Israel meets AI - Online MeetUp Series
(1) RNN & LSTM
Thursday, May 14, 2020
(2) Reinforcement Learning 
Wednesday, May 27 2020
(3) Online Deep Learning 
Thursday, June 11 2020

Reinforcement Learning: Value-Based Methods.

November 20, 2019, Microsoft,  Tel-Aviv.

Machine Learning in Finance.

December 3, 2019, Panda, Haifa.