professor • ​author • ​top researcher​ • evolutionary algorithms • machine learning • deep learning​ • ~40 grads • ​200+ publications • 7 books • awards ​
"A little perspective. That's it. I'd like some fresh, clear, well-seasoned perspective. Can you suggest a good wine to go with that?" 
​Anton Ego, Ratatouille 🐭
sipper@bgu.ac.il, ​Dept. Computer Science, Ben-Gurion Univ., Beer-Sheva 84105, Israel, (972)-8-6477880, Alon Building 37/121
scholar, github, linkedin, youtube, orcid, medium
SHORT POSTS 🦜
♢ Evolutionary Adversarial Attacks on Deep Networks
​♢ Evolutionary Algorithms, Genetic Programming, and Learning
♢ Evaluating Hyperparameters in Machine Learning
♢ Building Activation Functions for Deep Networks
♢ Two’s Company, Three’s an Ensemble
♢ Strong(er) Gradient Boosting​
♢ The Permutation Test: A Statistical Test that has (More than) Survived the Test of Time
♢ Superintelligence: Supergood or Superbad?
♢ The Aliens Have Landed—But They're Not Smart Enough to Take Over
RECENT PAPERS​ 🧻
♢ A Melting Pot of Evolution and Learning
♢ Patch of Invisibility: Naturalistic Black-Box Adversarial Attacks on Object Detectors
​♢ Classy Ensemble: A Novel Ensemble Algorithm for Classification
♢ Foiling Explanations in Deep Neural Networks
♢​ EC-KitY: Evolutionary Computation Tool Kit in Python
♢ Artificial General Intelligence: Pressure Cooker or Crucible?
♢ High Per Parameter: A Large-Scale Study of Hyperparameter Tuning for Machine Learning Algorithms
♢ An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networks
♢ Adaptive Combination of a Genetic Algorithm and Novelty Search for Deep Neuroevolution
♢ Combining Deep Learning with Good Old-Fashioned Machine Learning
♢ AddGBoost: A Gradient Boosting-Style Algorithm Based on Strong Learners
♢ Evolution of Activation Functions for Deep Learning-Based Image Classification
♢ From Requirements to Source Code: Evolution of Behavioral Programs
♢ Binary and Multinomial Classification through Evolutionary Symbolic Regression
♢ Neural Networks with À La Carte Selection of Activation Functions
♢ Symbolic-Regression Boosting
♢ Conservation Machine Learning: A Case Study of Random Forests
♢ Conservation Machine Learning
​♢ New Pathways in Coevolutionary Computation
♢ Automated discovery of test statistics using genetic programming
♢ Investigating the parameter space of evolutionary algorithms
♢ Evolutionary computation: the next major transition of artificial intelligence?
Picture
BIOGRAPHY 🧬
​Moshe Sipper is a professor of computer science at Ben-Gurion University of the Negev, Israel. He received the BA degree from the Technion — Israel Institute of Technology, and the MSc and PhD degrees from Tel Aviv University, all in computer science. During 1995–2001 he was a senior researcher at the EPFL (Switzerland), and during 2016-2020 he was a visiting professor at the University of Pennsylvania (USA).

​His current research focuses on evolutionary computation, machine learning, artificial intelligence​, and deep learning. At some point or other he also did research in: artificial life, artificial self-replication, bio-inspired computing, cellular automata, cellular computing, embryonic electronics, evolvable hardware, fuzzy logic, games, robotics, and software engineering.

Dr. Sipper has authored over 200 scientific publications, including three books: Evolved to Win, Machine Nature: The Coming Age of Bio-Inspired Computing, and Evolution of Parallel Cellular Machines: The Cellular Programming Approach. He has supervised close to 40 graduate students, and taught numerous basic and advanced courses in computer science, both undergraduate and graduate.

He is an associate editor of the journal Genetic Programming and Evolvable Machines, and was an associate editor of the journals: IEEE Transactions on Evolutionary Computation, IEEE Transactions on Computational Intelligence and AI in Games, and Memetic Computing. He organized and chaired several conferences and has served on the program committees of over 130. He has also served as a reviewer for nearly 40 journals and funding agencies.

Dr. Sipper won the 2015 IEEE CIS Outstanding TCIAIG Paper Award, the 2008 BGU Toronto Prize for Academic Excellence in Research, the 1999 EPFL Latsis Prize, and 6 HUMIE Awards (Human-Competitive Results Produced by Genetic and Evolutionary Computation). He has been cited as a top scientist, appears in the top 2% in the Mendeley list, and was one of 5 Scientists At The Forefront Of Computing And AI.
​
He is the author of four fiction books: Fredric: A Collection of Flash Fiction, Daniel Max and the King in the Tower, Xor: The Shape of Darkness, and The Peaceful Affair. He is also a cartoonist and has been known to sing.
Looking for grad advisor? ​Click here