| ... | ... | @@ -37,9 +37,6 @@ The Orga Team is by no means a closed circle, new members are welcome at any tim |
|
|
|
* October 22 Emre Neftci (PGI-15, Neuromorphic Software Ecosystems)
|
|
|
|
* November 22 Susanne Wenzel (INM-1, Big Data Analytics Group)
|
|
|
|
|
|
|
|
|
|
|
|
### How to select papers
|
|
|
|
tbd
|
|
|
|
|
|
|
|
|
|
|
|
## Next Meeting
|
| ... | ... | @@ -57,7 +54,7 @@ Passcode: 059545 |
|
|
|
[Claudio Gallicchio](https://sites.google.com/site/cgallicch/), Università di Pisa
|
|
|
|
claudio.gallicchio@unipi.it
|
|
|
|
|
|
|
|
update 28.11.22 [[22-12-28-Gallicchio-ReservoirComputing_beyond22.pdf](uploads/f8c65ba881ab3f5e55a24dade453cefe/22-12-28-Gallicchio-ReservoirComputing_beyond22.pdf)]
|
|
|
|
update 28.11.22 [[slides](uploads/f8c65ba881ab3f5e55a24dade453cefe/22-12-28-Gallicchio-ReservoirComputing_beyond22.pdf)]
|
|
|
|
|
|
|
|
#### Abstract
|
|
|
|
Reservoir Computing is an appealing methodology to design deep neural networks for temporal data processing that is strikingly efficient in terms of required computational resources. The core working principle resides in imposing dynamical stability properties to the developed neural representations, and restricting the training algorithms to operate on a small set of connections. After an introduction to the topic, this seminar will delve into recent advances that enable state-of-the-art performance in problems on temporal and graph-structured data, at a fraction of the cost required by fully trainable models.
|
| ... | ... | @@ -489,4 +486,4 @@ A training schedule using filter pruning and orthogonal reinitialization |
|
|
|
|
|
|
|
|
|
|
|
---
|
|
|
|
last change: 23.11.2022 sw |
|
|
\ No newline at end of file |
|
|
|
last change: 28.11.2022 sw |
|
|
\ No newline at end of file |
