Schematic of awake-dreaming learning. (a) Awake phase: over 100 real frames, the agent and model networks interact with the Pong environment. (b) Dreaming phase: over 50 imaginary frames, the agent is disconnected from the real environment and instead interacts only with the world model. This alternation between real and simulated experience boosts sample efficiency.
#Spiking #neural #networks (#SNN) running on continuous-time, noisy, and highly variable computing substrates can learn reliably with #ReinforcementLearning ... Not only in real brains, but also in mixed-signal #neuromorphic hardware! 😇
Neuromorphic dreaming […]
[Original post on fediscience.org]
12.10.2025 21:27 — 👍 6 🔁 2 💬 0 📌 0
What is this "neuromorphic" hype all about?
Here's my (neuro)view on it:
https://www.cell.com/neuron/fulltext/S0896-6273(25)00708-1
03.10.2025 15:56 — 👍 0 🔁 0 💬 0 📌 0
I'm extremely proud of the work of Maryada, Saray Soldado-Magraner and colleagues, in collaboration with Dean Buonomano, which shows how their cross-homeostatic #plasticity model enables analog #neuromorphic #circuits to produce stable recurrent dynamics on […]
[Original post on fediscience.org]
01.07.2025 12:44 — 👍 0 🔁 0 💬 0 📌 0
One more step toward EEG based epileptic seizure detection using #neuromorphic #spiking neural network chips!
rdcu.be/ek2SC
Jim Bartels, Olympia Gallou, Hiroyuki Ito, Matthew Cook, Johannes Sarnthein, Giacomo Indiveri & Saptarshi Ghosh
07.05.2025 21:52 — 👍 9 🔁 4 💬 0 📌 0
Yet another demonstration of how noisy analog #neuromorphic circuits can achieve impressive results in emulating real neural processing systems, implement always-on on-chip #learning, and solving practical #edge-computing applications!
@giacomoi.bsky.social
02.04.2025 20:42 — 👍 2 🔁 1 💬 0 📌 0
Original post on fediscience.org
I am really proud to announce that our latest effort on showing the advantages of our analog/digital #neuromorphic spiking neural network chips in solving complex biomedical applications has just been published here: https://rdcu.be/ef5N0
The demonstrates that *small* *highly variable* and *low […]
02.04.2025 20:25 — 👍 2 🔁 1 💬 0 📌 0
Image of #emacs #mu4e email program with zero messages in the inbox highlighted by a red circle
After >6 months of struggles, thanks to the holidays and to #emacs incredible time management options, I managed to reach this achievement again: #zeroinbox !!! 😅
#emacs, #org, #mu4e
06.01.2025 15:29 — 👍 1 🔁 0 💬 0 📌 0
Great start of the new year!
A new manuscript just published showing yet again how design principles and strategies from biological perceptive systems enable robust processing on analog #neuromorphic electronic systems, despite their variability!
https://rdcu.be/d5o0d
03.01.2025 10:45 — 👍 0 🔁 0 💬 0 📌 0
Original post on fediscience.org
Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!
It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite […]
31.12.2024 17:10 — 👍 0 🔁 1 💬 0 📌 0
Carver Mead and Misha Mahowald in Carverland in the early 90's looking at #neuromorphic chip measurement results.
Cross-posting this for the new colleagues and friends on BlueSky that recently decided to ditch X :)
Anybody interested in #neuromorphic, should really read Carver Mead's acceptance speech for the "2023 Misha Mahowald Recognition of Lifetime Contribution to […]
[Original post on fediscience.org]
01.12.2024 23:35 — 👍 1 🔁 0 💬 0 📌 0
