arXiv subjects

Fabian Chersi

Publications and source records attributed to Fabian Chersi.

3 recordsLinked to original sources

arXiv2026

It Takes Few to TANGO: A Quantized Distributed Model for Binaural Speech Enhancement

Neural network-based multichannel speech enhancement systems achieve strong enhancement performance, but their computational and memory requirements limit deployment on resource-constrained devices. This paper investigates low-precision inference for TANGO, a hybrid distributed binaural speech enhancement system combining neural mask estimation with spatial filtering. We evaluate post-training quantization and quantization-aware training for the neural components, and analyze how quantization errors in the mask estimators propagate through the downstream spatial filtering stage. Our analysis shows that, although quantization degrades intermediate mask estimates, the spatial filtering stage compensates for most quantization-induced errors. Leveraging this robustness, we simplify TANGO into MN-TANGO, reducing both model size and computational complexity while maintaining comparable final performance. By combining INT8 weight-and-activation quantization with ERB compression and grouped recurrent layers, the most compact MN-TANGO reaches 4.65 MMAC/s and 0.177 MB.

cs.SD↗

arXiv2018

When Conventional machine learning meets neuromorphic engineering: Deep Temporal Networks (DTNets) a machine learning frawmework allowing to operate on Events and Frames and implantable on Tensor Flow Like Hardware

We introduce in this paper the principle of Deep Temporal Networks that allow to add time to convolutional networks by allowing deep integration principles not only using spatial information but also increasingly large temporal window. The concept can be used for conventional image inputs but also event based data. Although inspired by the architecture of brain that inegrates information over increasingly larger spatial but also temporal scales it can operate on conventional hardware using existing architectures. We introduce preliminary results to show the efficiency of the method. More in-depth results and analysis will be reported soon!

cs.NE↗

arXiv2014

The hippocampal-striatal circuit for goal-directed and habitual choice

It is now widely accepted that one of the roles of the hippocampus is to maintain episodic spatial representations, while parallel striatal pathways contribute to both declarative and procedural value computations by encoding different input-specific outcome predictions. In this paper we investigate the use of these brain mechanisms for action selection, linking them to model-based and model-free controllers for decision making. To this aim we propose a biologically inspired computational model that embodies these theories and explains the functioning of the hippocampal-striatal circuit in a rat navigation task. Its main characteristic is to allow the cooperation of habitual and goal-directed behaviors, with the hippocampus primarily involved in encoding spatial information and simulating possible navigation paths, and the ventral and dorsal striatum involved in learning stimulus-response behaviors and evaluating the reward expectancies associated to predicted locations and sensed stimuli, respectively. The architecture we present employs an unsupervised reinforcement learning rule for the hippocampal-striatal network that is able to build a representation of the environment in which rewarding sites and informative landmarks produce value gradients that are used for planning and decision making. Additionally, it utilizes an arbitration mechanism that balances between exploitation, i.e. stimulus-response behaviors, and mental exploration, i.e. motor imagery processes, based on the intensity and the variability of the responses of striatal neurons. We interpret these results in light of recent experimental data that show anticipatory activations in hippocampal and striatal areas.

q-bio.NC↗