Haim Sompolinsky retweeted
בגאווה ישראלית גדולה בירכתי היום את פרופסור חיים סומפולינסקי מהאוניברסיטה העברית בירושלים על זכייתו בפרס Lundbeck היוקרתי - הפרס החשוב ביותר בעולם בתחום חקר המוח. מדובר בהישג ישראלי פורץ דרך, שמשקף את מצוינות האקדמיה הישראלית במחקר ובכלל.
אני סמוך ובטוח כי בעקבותיו יבואו עוד אותות ופרסים שיוקירו את תרומתם של ישראליות וישראלים לקהילה המדעית העולמית, ומקווה ופועל לכך שנדע להכיר תודה - כחברה וכמדינה - לענקי האקדמיה והמחקר שלנו.
Topics include principles of early sensory processing; unsupervised and supervised learning; attractors, memory, and spatial functions in cortical circuits; noise, chaos, and neural coding; learning, representations, and cognition in deep neural networks in brains and AI. 3/3
The course introduces analytical and numerical tools from information theory, dynamical systems, statistics, statistical physics, AI, and machine learning for the study of neural computation. 2/3
My Harvard/Neuro 231, 2024 Edition begins soon. It explores contemporary brain theory spanning local neuronal circuits as well as deep neural networks. It examines the relationship between network structure, dynamics, and computation. 1/3
The theory unites NTK and NNGP as two limits of the same underlying process. We introduce the Neural Dynamical Kernel (NDK), derive equations for the dynamics of the mean predictor of the network, and discuss implications for the problem of representational drift in neuroscience.
I am excited to announce a recent work by Yehonatan Avidan and Qianyi Li arxiv.org/abs/2309.04522
presenting an analytical theory for learning dynamics in infinitely wide neural network.
Jet Blue just entered the Book of Guinness for World Record on Greediness. It cancelled my flight due to weather conditions but refused to fully refund me. They charged me cancellation fee! Never underestimate the creative way companies such as Jet Blue chase your money! advice?
Our model proposes a novel scheme for associative memory of temporal sequence. In contrast to using sequence attractors (Sompolinsky and Kanter, 1988),
here entire sequences are stored holistically as fixed points-a scheme that is robust to overlap between sequences.
and then store multiple compressed vectors as fixed points in RNN. Retrieved fixed points is followed by decoding individual linked components. Thus, model consists of two memory systems: 'dictionary' for items and 'episodic' for their linked structures.
However real-life memory must be able to store multiple knowledge structures each composed of connected building blocks, such as episodes, cognitive maps and temporal sequences. To tackle this problem we first compress structures into fixed-length distributed representations
I am excited to announce the publication of the wonderful paper of Julia Steinberg on Associative memory of structured knowledge in scientific reports
nature.com/articles/s41598-0…. Most neural models of associative memory store structureless knowledge as simple random patterns in RNNs
Haim Sompolinsky retweeted
We highlight a study by Ben Sorscher, @SuryaGanguli and @HSompolinsky in which they explore a quantitative theory of neural geometry and few shot learning in deep neural networks and in macaque inferotemporal cortex (rdcu.be/cZCJ3). nature.com/articles/s43588-0…
Haim Sompolinsky retweeted
Our new paper @NeuroCellPress "A unified theory for the computational and mechanistic origins of grid cells" lead by Ben Sorscher & @meldefon w/@SamOcko & @lisa_giocomo explains when & why grid cells appear (or don't) in trained neural path-integrators and
authors.elsevier.com/c/1f~Ze…
Haim Sompolinsky retweeted
Our new paper in @PNASNews: "Neural representation representation geometry underlies few shot concept learning'' lead by Ben Sorscher and @HSompolinsky: a quantitative theory of neural geometry & few shot learning, tested in both deep networks & monkey IT pnas.org/doi/abs/10.1073/pna…
