CRNS Talk Series (10) – Live Talk by Dr. Dileep George – Google DeepMind – USA

November 30th, 2022 Daniela Lopez de Luise
The Center for Robotics and Neural Systems (CRNS) is pleased to announce the talk of Dr. Dileep George from Google DeepMind – USA on Wednesday, November 30th from 3:00 PM to 4:30 PM  (London time) over Zoom. Thank you for forwarding the invitation to any of your colleagues who might be interested.
>> Events: The CRNS talk series will cover a wide range of topics including social and cognitive robotics, computational neuroscience, computational linguistics, cognitive vision, machine learning, AI, and applications to healthcare. More details are available here:
>> Link for the next event (No Registration is Required): 

Join Zoom Meeting
>> Title of the talk:  Reverse engineering cortical microcircuit models of visual perception

Abstract:

Although deep learning has made tremendous strides in visual recognition and generation, a significant gap remains between human and machine perception. In this talk, I will argue that models that use stochastic variables, lateral interactions, and dynamic inference might be required to close this gap. I will then describe a generative model, Recursive Cortical Networks (RCN), that partially meets these requirements and demonstrated excellent performance on some visual task benchmarks.

Using RCN we derive a family of anatomically instantiated and functional cortical circuit models. Efficient inference and generalization guided the representational choices in the original computational model. The cortical circuit model is derived by systematically comparing the computational requirements of this model with known anatomical constraints. The derived model suggests precise functional roles for the feed-forward, feedback, and lateral connections observed in different laminae and columns, assigns a computational role for the path through the thalamus, predicts the interactions between blobs and interblobs, and offers an algorithmic explanation for the innate inter-laminar connectivity between clonal neurons within a cortical column. The model also explains several visual phenomena, including the subjective contour effect, and neon-color spreading effect, with circuit-level precision. Our work paves a new path forward in understanding the logic of cortical and thalamic circuits.

>> If you have any questions, please don't hesitate to contact me, 

Regards

Live e-Lecture by Prof. Dr. Laura Leal-Taixé: “From Handcrafted to EndEnd Learning, and Back: a Journey for Multi-Object Tracking”, December 2nd, 2022 14.15/14.30 -16:00 CET

November 30th, 2022 Daniela Lopez de Luise

Dear AI scientist/engineer/student/enthusiast,

 

Prof. Dr. Laura Leal-Taixé, a prominent AI researcher internationally, will deliver the e-lecture: 

“From Handcrafted to End-to-End Learning, and Back: a Journey for Multi-Object Tracking”, on Tuesday December 2nd, 2022 14.15/14.30 -16:00 CET,

see details in: http://www.i-aida.org/ai-lectures/

 

This lecture is delivered through University of Modena and Reggio Emilia in cooperation with AIDA.

 

You can join for free using the zoom link: link

Attendance is free.

 

The International AI Doctoral Academy (AIDA), a joint initiative of the European R&D projects AI4Media, ELISE, Humane AI Net, TAILOR, VISION, currently in the process of formation,

is very pleased to offer you top quality scientific lectures on several current hot AI topics.

 

Lectures will be offered alternatingly by:

Top highly-cited senior AI scientists internationally or

Young AI scientists with promise of excellence (AI sprint lectures)

 

Other upcoming lecture:

 

Dr. Silvia Zuffi: “3D Computer Vision for Animals”, December 15th, 2022 14.15/14.30 -16:00 CET.

More lecture infos in: https://www.i-aida.org/events/3d-computer-vision-for-animals/

 

These lectures are disseminated through multiple channels and email lists (we apologize if you received it through various channels). 

If you want to stay informed on future lectures, you can register in the email lists AIDA email list and CVML email list.

 

Best regards

Profs. M. Chetouani, P. Flach, B. O’Sullivan, I. Pitas, N. Sebe, J. Stefanowski

Read More »

CBMS Deep Learning and Numerical PDEs, USA, Jun 2023

November 30th, 2022 Daniela Lopez de Luise

 

The Mathematics Department at Morgan State University is excited to

host the CBMS Conference: Deep Learning and Numerical PDEs, which will

take place at Morgan State University from June 19 – June 24, 2023.

 

This conference will bring together a diverse group of researchers

from PDE theory, scientific computing, and machine learning who work

on both the theoretical and applied aspects of solving PDEs using

neural networks. There will be a distinguished lecture series to be

delivered by Prof. Jinchao Xu (KAUST and Penn State) and invited

plenary talks from distinguished speakers in the one and half-day

workshop. Our goal is to present a comprehensive introduction to the

diverse set of research opportunities in machine learning for

scientific computing. We are also aiming to create an inclusive

environment geared toward exposing traditionally disadvantaged groups

to this important new field of research. Information about important

deadlines will be made available later this year.

 

For more information, please visit

https://sites.google.com/view/nsf-cbms-dl-nmpde/home

Read More »

Especialización en Higiene y Seguridad del Trabajo _ Edición 2023

November 29th, 2022 Daniela Lopez de Luise

Estimada/o colega,

En esta oportunidad te hacemos llegar información sobre la Especialización en Higiene y Seguridad del Trabajo, ofrecida por el Departamento de Seguridad del Trabajo y Ambiente de la FIUBA, que ya abrió sus inscripciones para la edición 2023.

En el archivo adjunto encontrarás toda la información respecto a la carrera.

IMPORTANTE: Para consultas, informes e inscripción,  por favor escribir  a: diat@fi.uba.ar / aperez@fi.uba.ar

Aprovechamos la ocasión para enviarte un afectuoso saludo,

Subsecretaría de Relación con Graduados FIUBA

image.png

pdf icon Carrera_de_especializacion_de_posgrado_Higiene_y_seguridad_en_el_trabajo_docx_07a72608be-1.pdf
Read More »

Free IEEE Live Stream Webinar

November 28th, 2022 Daniela Lopez de Luise


image.png
Carbon-Aware Computing @ Google, and Beyond
Free Live Stream webinar cosponsored by IEEE Students and IEEE Young Professionals
1 December 2022
1:30pm ET
Register here to receive an email reminder 10 minutes before the event
Abstract
The growing climate impact of increased Greenhouse Gas Emissions and CO2 levels in Earth's atmosphere highlights the value and importance of technologies that reduce such impact. Electricity generation is a significant contributor to global CO2 emissions, and the datacenter industry is expected to reach anywhere from 3 to 13% of global electricity demand by 2030. We share some conclusions derived from operational data and discuss the key technical challenges that drive carbon-aware designs and their future enhancements.
Speaker Bio
Ana Radovanovic has been a research scientist at Google since early 2008, after she earned her PhD Degree in Electrical Engineering from Columbia University (2005) and worked for 3 years as a Research Staff Member in the Mathematical Sciences Department at IBM TJ Watson Research Center. Nowadays, Ana is widely recognized as a technical lead and research entrepreneur. She is a Senior Staff Research Scientist, serving as a Technical Lead for Energy Analytics and Carbon Aware Computing at Google.
Read More »
« Older Entries
Newer Entries »
Design by 2b Consult