no code implementations • 25 Apr 2024 • Alessio Devoto, Simone Petruzzi, Jary Pomponi, Paolo Di Lorenzo, Simone Scardapane
In this paper, we propose a novel design for AI-native goal-oriented communications, exploiting transformer neural networks under dynamic inference constraints on bandwidth and computation.
no code implementations • 12 Mar 2024 • Simone Scardapane, Alessandro Baiocchi, Alessio Devoto, Valerio Marsocci, Pasquale Minervini, Jary Pomponi
This article summarizes principles and ideas from the emerging area of applying \textit{conditional computation} methods to the design of neural networks.
1 code implementation • 2 Feb 2024 • Jary Pomponi, Alessio Devoto, Simone Scardapane
The latter is a gated incremental classifier, helping the model modify past predictions without directly interfering with them.
1 code implementation • 15 Dec 2023 • Bartosz Wójcik, Alessio Devoto, Karol Pustelnik, Pasquale Minervini, Simone Scardapane
The computational cost of transformer models makes them inefficient in low-latency or low-power applications.