ICLM Journal Club

From LMP Journal Club
Revision as of 20:58, 27 September 2022 by Hmotanis (Talk | contribs) (This Friday - 30 September 2022 (9:30 a.m., in person, Gonda 1357))

Jump to: navigation, search

This Friday - 30 September 2022 (9:30 a.m., in person, Gonda 1357)

Speaker: Dean Buonomano

Title: How does the Natural Language AI model GPT-3 work?

Summary: Dramatic advances in machine learning and artificial intelligence (AI) have culminated in Natural Language Processing systems such as GPT-3, and image generation systems such as DALL-E. These deep neural network modes represent very complex learning systems with hundreds of billions of parameters. Much as neuroscientists struggle to understand how the brain works, the machine learning field is struggling with how AI's work. GPT-3 is a state-of-the-art deep neural network based on a "transformer" architecture. I will present a summary of GPT-3's architecture and training, and why it is very different from standard recurrent neural network approaches. We will also discuss the extent to which these AI models do or don't capture principles of biological neural networks.

Relevant Papers: Attention Is All You Need, Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin, NIPS (2017)

About Us


The Integrative Center for Learning and Memory (ICLM) is a multidisciplinary center of UCLA labs devoted to understanding the neural basis of learning and memory and its disorders. This will require a unified approach across different levels of analysis, including;

1. Elucidating the molecular cellular and systems mechanisms that allow neurons and synapses to undergo the long-term changes that ultimately correspond to 'neural memories'.

2. Understanding how functional dynamics and computations emerge from complex circuits of neurons, and how plasticity governs these processes.

3. Describing the neural systems in which different forms of learning and memory take place, and how these systems interact to ultimately generate behavior and cognition.

History of ICLM

The Integrative Center for Learning and Memory formally LMP started in its current form in 1998, and has served as a platform for many interactions and collaborations within UCLA. A key event organized by the group is the weekly ICLM Journal Club. For more than 10 years, graduate students, postdocs, principal investigators, and invited speakers have presented on topics ranging from the molecular mechanisms of synaptic plasticity, through computational models of learning, to behavior and cognition. Dean Buonomano oversees the ICLM journal club with help of student/post doctoral organizers. For other events organized by ICLM go to http://www.iclm.ucla.edu/Events.html.

Current Organizers:

Saray Soldado (Buonomano Lab) & Lukas Oesch (Churchland Lab). Please email us at iclm.journalclub@gmail.com if you would like to get regular updates regarding our journal club and weekly reminders.

Current Faculty Advisor:

Dean Buonomano

Past Organizers:

i) Anna Matynia(Aug 2004 - Jun 2008) (Silva Lab)

ii) Robert Brown (Aug 2008 - Jun 2009) (Balleine Lab)

iii) Balaji Jayaprakash (Aug 2008 - Nov 2011) (Silva Lab)

iv) Justin Shobe & Thomas Rogerson (Dec 2011 - June 2013) (Silva Lab)

v) Walt Babiec (O'Dell Lab) (2013-2014)

vi) Walt Babiec (O'Dell Lab) & Helen Motanis (Buonomano Lab) (2014-2017)

vii) Helen Motanis (Buonomano Lab) & Shonali Dhingra (Mehta Lab) (2017-2018)

viii) Shonali Dhingra (Mehta Lab) (2018-2020)

ix) Megha Sehgal (Silva Lab) & Giselle Fernandes (Silva Lab) (2020-2022)

Wiki Newbies

Consult the User's Guide for information on using the wiki software.