Публичные лекции

26 сентября 2019 года

00.00 - 00.00

Lecture 3: Active inference and artificial curiosity

О мероприятии

В рамках визита Карла Фристона будет организована серия мастер-классов

 

 

A masterclass in the free energy principle

 

 

This workshop comprises three lectures covering the various aspects of the free energy principle (delivered by its principal architect – Karl Friston); namely, biological self organisation in dynamical systems like the brain and how this leads to predictive coding and embodied (active) inference. The second lecture deals with equivalent formulations of active inference for models of the world that can be described in terms of discrete states (and time steps). The final lecture will consider recent advances in Bayesian model selection and averaging in the brain that provide a formalism for artificial curiosity and insight.

 

 

Lecture 3: Active inference and artificial curiosity.

 

This talk offers a formal account of insight and learning in terms of active (Bayesian) inference. It deals with the dual problem of inferring states of the world and learning its statistical structure. In contrast to current trends in machine learning (e.g., deep learning), we focus on how agents learn from a small number of ambiguous outcomes to form insight. I will simulations of abstract rule-learning and approximate Bayesian inference to show that minimising (expected) free energy leads to active sampling of novel contingencies. This epistemic, curiosity-directed behaviour closes ‘explanatory gaps’ in knowledge about the causal structure of the world; thereby reducing ignorance, in addition to resolving uncertainty about states of the known world. We then move from inference to model selection or structure learning to show how abductive processes emerge when agents test plausible hypotheses about symmetries in their generative models of the world. The ensuing Bayesian model reduction evokes mechanisms associated with sleep and has all the hallmarks of ‘aha moments’.

 

 

Рабочий язык мероприятия: английский.

О месте проведения лекции сообщим дополнительно.

Программа мероприятия

Lecture 3: Active inference and artificial curiosity.

This talk offers a formal account of insight and learning in terms of active (Bayesian) inference. It deals with the dual problem of inferring states of the world and learning its statistical structure. In contrast to current trends in machine learning (e.g., deep learning), we focus on how agents learn from a small number of ambiguous outcomes to form insight. I will simulations of abstract rule-learning and approximate Bayesian inference to show that minimising (expected) free energy leads to active sampling of novel contingencies. This epistemic, curiosity-directed behaviour closes ‘explanatory gaps’ in knowledge about the causal structure of the world; thereby reducing ignorance, in addition to resolving uncertainty about states of the known world. We then move from inference to model selection or structure learning to show how abductive processes emerge when agents test plausible hypotheses about symmetries in their generative models of the world. The ensuing Bayesian model reduction evokes mechanisms associated with sleep and has all the hallmarks of ‘aha moments’.

 

Пост-релиз мероприятия

Условия участия

Данное мероприятие пройдет в  НИУ ВШЭ (Национальный исследовательский университет Высшая школа экономики), адрес места проведения сообщим дополнительно.

 

Лекция на английском языке (без перевода).

 

Для прохода в здание НИУ ВШЭ при себе иметь документ, удостоверяющий личность.

 

Приглашаем всех желающих!

Форма регистрации на мероприятие (в своем личном кабинете Вы сможете отслеживать посещенные мероприятия)

Дата: 26 сентября 2019 года

Время: 00.00 - 00.00

Email : nirs@mgppu.ru

Телефон:

Организатор: Лекция пройдет в НИУ ВШЭ (место проведения уточняется)

Место проведения:

Как добраться:

Ближайшие мероприятия

Публичные лекции

24.09.2019

МГППУ, Сретенка 29

Публичные лекции

25.09.2019

МГППУ, Сретенка 29

© 2018 Московский государственный психолого-педагогический университет