Aller au contenu principal

Online research seminar "Achieving Energy-Efficient Artificial Intelligence with Brain Inspiration" on November 10 from 12:30 to 1:30 pm

2022-11-10 12:30 2022-11-10 13:30 Online research seminar "Achieving Energy-Efficient Artificial Intelligence with Brain Inspiration" on November 10 from 12:30 to 1:30 pm

Presentation of the theme of the seminar:

When performing artificial intelligence (AI) tasks, computers consume considerably more energy for moving data between logic and memory units than for doing actual arithmetic. This inefficiency leads to the unsustainable energy cost of AI: training modern AI models uses gigawatt-hours of electricity.

Brains, by contrast, achieve superior energy efficiency by fusing logic and memory entirely, performing a form of “in-memory” computing. Until now such an integration between logic and memory was impossible at a large scale using CMOS technology. However, companies such as Intel, Samsung, ST Microelectronics, or TSMC, have recently reached production status on new memory devices such as (mem)resistive, phase change, and magnetic memories, which give us an opportunity to achieve an extremely tight integration between logic and memory. Unfortunately, these new devices also come with important challenges due to their unreliable nature.

Link to connect

Research seminar program:

In this talk, we will look at neuroscience inspiration to extract lessons on the design of in-memory computing systems with unreliable devices.

  • We will first study the reliance of brains on approximate memory strategies, which can be reproduced for machine learning. We will give the example of a memristor-based Bayesian machine. Based on measurements on a hybrid CMOS/memristor chip, we will see that such a system can recognize human gestures using thousands times less energy than a competing microcontroller unit.
  • Then, we will present a second approach where the probabilistic nature of emerging memories, instead of being mitigated, can be fully exploited to implement a type of probabilistic learning. We train experimentally an array of 16,384 memristors to recognize images of cancerous tissues using this technique.
  • Finally, we will present prospects concerning the implementation of different learning algorithms with emerging memories.

Practical information

Who is Damien Querlioz?

Damien Querlioz is a CNRS Researcher at the Centre de Nanosciences et de Nanotechnologies of Université Paris-Saclay and CNRS.
His research focuses on novel usages of emerging non-volatile memory and other nanodevices, in particular relying on inspirations from biology and machine learning. He received his predoctoral education at Ecole Normale Supérieure, Paris and his PhD from Université Paris-Sud in 2009. Before his appointment at CNRS, he was a Postdoctoral Scholar at Stanford University and at the Commissariat à l'Energie Atomique.

Damien Querlioz is the coordinator of the interdisciplinary INTEGNANO research group, with colleagues working on all aspects of nanodevice physics and technology, from materials to systems. He is a member of the bureau of the French Biocomp research network. He has co-authored one book, nine book chapters, more than 150 journal articles, and conference proceedings, and given more than 80 invited talks at national and international workshops and conferences.

In 2016, he was the recipient of an ERC Starting Grant to develop the concept of natively intelligent memory. In 2017, he received the CNRS Bronze medal. He has also been a co-recipient of the 2017 IEEE Guillemin-Cauer Best Paper Award and of the 2018 IEEE Biomedical Circuits and Systems Best Paper Award.

More information about him

Online
Thematic : Research

In this research seminar, we will look at neuroscience inspiration to extract lessons on the design of in-memory computing systems with unreliable devices, with Damien Querlioz, a CNRS Researcher.

  • Public
    Tout public
  • Event type
    Conférence / séminaire / webinaire
  • Conditions

    Entrée libre

  • Dates
    Thursday 10 November, 12:30
    12:30 pm - 01:30 pm
  • Location
    Online

Presentation of the theme of the seminar:

When performing artificial intelligence (AI) tasks, computers consume considerably more energy for moving data between logic and memory units than for doing actual arithmetic. This inefficiency leads to the unsustainable energy cost of AI: training modern AI models uses gigawatt-hours of electricity.

Brains, by contrast, achieve superior energy efficiency by fusing logic and memory entirely, performing a form of “in-memory” computing. Until now such an integration between logic and memory was impossible at a large scale using CMOS technology. However, companies such as Intel, Samsung, ST Microelectronics, or TSMC, have recently reached production status on new memory devices such as (mem)resistive, phase change, and magnetic memories, which give us an opportunity to achieve an extremely tight integration between logic and memory. Unfortunately, these new devices also come with important challenges due to their unreliable nature.

Link to connect

Research seminar program:

In this talk, we will look at neuroscience inspiration to extract lessons on the design of in-memory computing systems with unreliable devices.

  • We will first study the reliance of brains on approximate memory strategies, which can be reproduced for machine learning. We will give the example of a memristor-based Bayesian machine. Based on measurements on a hybrid CMOS/memristor chip, we will see that such a system can recognize human gestures using thousands times less energy than a competing microcontroller unit.
  • Then, we will present a second approach where the probabilistic nature of emerging memories, instead of being mitigated, can be fully exploited to implement a type of probabilistic learning. We train experimentally an array of 16,384 memristors to recognize images of cancerous tissues using this technique.
  • Finally, we will present prospects concerning the implementation of different learning algorithms with emerging memories.

Practical information

Who is Damien Querlioz?

Damien Querlioz is a CNRS Researcher at the Centre de Nanosciences et de Nanotechnologies of Université Paris-Saclay and CNRS.
His research focuses on novel usages of emerging non-volatile memory and other nanodevices, in particular relying on inspirations from biology and machine learning. He received his predoctoral education at Ecole Normale Supérieure, Paris and his PhD from Université Paris-Sud in 2009. Before his appointment at CNRS, he was a Postdoctoral Scholar at Stanford University and at the Commissariat à l'Energie Atomique.

Damien Querlioz is the coordinator of the interdisciplinary INTEGNANO research group, with colleagues working on all aspects of nanodevice physics and technology, from materials to systems. He is a member of the bureau of the French Biocomp research network. He has co-authored one book, nine book chapters, more than 150 journal articles, and conference proceedings, and given more than 80 invited talks at national and international workshops and conferences.

In 2016, he was the recipient of an ERC Starting Grant to develop the concept of natively intelligent memory. In 2017, he received the CNRS Bronze medal. He has also been a co-recipient of the 2017 IEEE Guillemin-Cauer Best Paper Award and of the 2018 IEEE Biomedical Circuits and Systems Best Paper Award.

More information about him