Information Theory SG Seminar
24 events
-
Seminar
Quantum Wasserstein distance of order 1
December 16 (Wed) at 13:00 - 14:30, 2020
Ryusuke Hamazaki (Senior Research Scientist, iTHEMS / RIKEN Hakubi Team Leader, Nonequilibrium Quantum Statistical Mechanics RIKEN Hakubi Research Team, RIKEN Cluster for Pioneering Research (CPR))
The Wasserstein distance is an indicator for the closeness of two probability distributions and is applied to various fields ranging from information theory to neural networks [1]. It is particularly useful to treat the geometry of the underlying space, such as tensor-product structures. In this journal club, I talk about one of the recent proposals on quantum extension of the Wasserstein distance [2]. After reviewing basic properties of classical Wasserstein distance, e.g., its relation to concentration phenomena, I discuss how they might be generalized to quantum realm.
Venue: via Zoom
Event Official Language: English
-
Seminar
Statistical model for meaning representation of language
December 16 (Wed) at 10:30 - 12:00, 2020
Koichiro Yoshino (Team Leader, Robotics Project, RIKEN Cluster for Science, Technology and Innovation Hub (RCSTI))
One of the final goals of natural language processing is building a model to capture the semantic meaning of language elements. Language modeling is a recent research trend to build a statistical model to express the meaning of language. The language model is based on the distributional hypothesis. The distributional hypothesis indicates that the surrounding elements of the target element describe the meaning of the element. In other words, relative positions between sentence elements (morphologies, words, and sentences) are essential to know the element's meaning. Recent works on distributed representation mainly focus on relations between clear elements: characters, morphologies, words, and sentences. However, it is essential to use structural information of languages such as dependency and semantic roles for building a human-understandable statistical model of languages. In this talk, we describe the statistical language model's basis and then discuss our research direction to introduce the language structure.
Venue: via Zoom
Event Official Language: English
-
Seminar
Journal Club of Information Theory SG II
December 8 (Tue) at 13:00 - 14:00, 2020
Akinori Tanaka (Senior Research Scientist, iTHEMS)
The practical updating process of deep neural networks based on stochastic gradient descent is quite similar to stochastic dynamics described by Langevin equation. Under the Langevin system, we can "derive" 2nd law of thermodynamics, i.e. increasing the total entropy of the system. This fact suggests "2nd law of thermodynamics in deep learning." In this talk, I would like to explain this idea roughly, and there will be no concrete new result, but it may provide us new perspectives to study neural networks, I hope.
Venue: via Zoom
Event Official Language: English
-
Seminar
Journal Club of Information Theory SG
December 1 (Tue) at 13:00 - 14:00, 2020
Akinori Tanaka (Senior Research Scientist, iTHEMS)
The practical updating process of deep neural networks based on stochastic gradient descent is quite similar to stochastic dynamics described by Langevin equation. Under the Langevin system, we can "derive" 2nd law of thermodynamics, i.e. increasing the total entropy of the system. This fact suggests "2nd law of thermodynamics in deep learning." In this talk, I would like to explain this idea roughly, and there will be no concrete new result, but it may provide us new perspectives to study neural networks, I hope. *Detailed information about the seminar refer to the email.
Venue: via Zoom
Event Official Language: English
24 events