Day 1: Welcome and history of neuromorphic engineering

By

Welcome everyone to this workshop's daily blog.

Chiara Bartolozzi welcomed everyone to the start of the workshop.

Two new things this year:

  1. Discussion leaders will select 2 people from audience to lead questions
  2. Organizers will select a single moderator for each session

Chiara B pointed out that the main aim of the workshop is to discuss future directions in light of SOA.

Andre van Schaik suggested that to network, people should sit with different people at each meal.

Giacomo Indiveri showed everyone some main features of new IT setup and who is doing this support (Kathrin Aguilar, Simone Schumacher, Chiara de Luca, Noah Lawrence).   The hotel finally has a wired 900Mbps connection, which should improve things compared to the cross-water wireless internet of previous years.

Saray Soldado, Andre and Chiara B organized the program and selected the participants for the roughly 100 people who fit in the hotel.

The program overview is planned to be 

Internal and post workshop communication

  1. Local communication will be via https://mm.neuromorphs.net (special instructions sent to participants for local access with correct DNS setup using public google DNS 8.8.8.8).
  2. https://forum.neuromorphs.net will be used later for post-workshop announcements.

History of NE

Giacomo went on to recount some of the rich history of neuromorphic engineering, starting with Nobukatzu Fukushima in Japan in early 1970s, then Carver Mead at the pcmp (physics of computation) lab at Caltech in middle 1980s, followed by Eric Vittoz in Switzerland. Andre told the story of the trackball chip from Logitech that originated from this work that just ended production in 2024, and Tobi Delbruck mentioned how Synaptics (which started as the original neuromorphic Silicon Valley AI startup) ended up dominating the world supply of touchpads.

Then Tobi described how CAVIAR was a seminal project involving pure NE chip designers with a built-in customer-supplier market that resulted in the DVS event camera, and Elisabetta Chicca talked about Daniel Amit in Rome developed some of the original on-chip learning ideas.

Giacomo concluded the first session by quoting from Carver's 2023 NECO paper "Neuromorphic Engineering in memory of Misha Mahowald".

Finally Matthew Cook drew a chart to show how AI grew, stagnated, and then grew dramatically, crossing mention on google ngrams with "digital logic" (for whatever that means) last year. And how working with mismatched neurons and clipping nonlinearities like ReLU, the idea of disinhibition became valuable while mathematicians regard it simply as a double negation identity.

That brought us to a dead laptop battery and the coffee break under beautiful clearing skies, hot sun, and a totally calm sea.

After the break

Chiara B and Sergio Solinas announced the call for t-shirt logo for shirts that will cost about 10 euro.

Giacomo listed 4 categories of questions or goals and asked participants to place themselves in these categories.  Here is a photo of these boards after the round of participants self-intros.


That brought us to snorkeling under brilliant sun and crystal clear water followed by the usual fantastic lunch.

Afternoon and evening

Workgroups introduced themselves and showed their demos in the disco. More about this tomorrow.

On behalf of this year's bloggers, see you tomorrow.







Comments

Post a Comment

Popular posts from this blog

Day 7: Future Neuromorphic Technologies with G. Indiveri, M. Payvand, R. Sepulchre and S.C. Liu

By
Image
Author : Shreya Kshirasagar Following an exhilarating weekend adventure in Alghero - packed with late night disco, hiking, climbing, windsurfing, and a variety of other thrilling sports - everyone has returned revitalized and brimming with enthusiasm for the second half of CapoCaccia’25. It's time to channel this energy and make the most of our upcoming experiences! Giacomo announced the speakers for the day. Gentle reminder to all the readers to upload the content on the cloud server. A thought-provoking discussion highlights the enduring relevance of John Platt’s 1964 paper on  “strong inference”, a rigorous approach to experimental science (physics, biology, neuroscience, etc.). The core idea? Design experiments to  maximize uncertainty , ensuring outcomes are equally likely to confirm  or  refute your hypothesis. This contrasts with common practices where experiments are biased toward confirming preconceived ideas, a pitfall in fields like biology and engineering...
Read more

Day 2: Evolution of Neural Circuits, Eulogy for Yves Frégnac - Gilles Laurent and Florian Engert

By
Image
Evolution's Playbook: Convergence, Inheritance, and the Making of Brains: Gilles Laurent and Florian Engert Today's first session shifted our focus from the how of building neural circuits to the why they are the way they are. Led by Gilles Laurent , we explored the long timescales that have shaped nervous systems across the animal kingdom. Setting the Stage: Deep Time and Shared Origins Gilles began by laying out the timescales at which evolution operates. Life itself arose remarkably early on Earth (~4 billion years ago), with fundamental molecular building blocks like ion channels and neurotransmitter systems appearing long before complex nervous systems, often originating in single-celled organisms like bacteria. Neurons took a lot longer to appear on the stage, something like 600 million years ago. This coincides with the Precambrian/Cambrian boundary, where animal life diversified explosively, setting lineages like ours (vertebrates) and cephalopods or insects on indepe...
Read more