Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks

Detailed Info Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks Authors:Gianmarco Cerutti, Renzo Andri, Lukas Cavigelli, Michele Magno, Elisabetta Farella, Luca Benini.Title:Sub-mW Keyword Spotting…

Continue ReadingSub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks

Multi-Exit Vision Transformer for Dynamic Inference

  • Post category:Publications

Underspecification and fairness in machine learning (ML) applications have recently become two prominent issues in the ML community. Acoustic scene classification (ASC) applications have so far remained unaffected by this discussion, but are now becoming increasingly used in real-world systems where fairness and reliability are critical aspects.

Continue ReadingMulti-Exit Vision Transformer for Dynamic Inference

Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning

  • Post category:Publications

Deploying deep learning services for time-sensitive and resource-constrained settings such as IoT using edge computing systems is a challenging task that requires dynamic adjustment of inference time. Multi-exit architectures allow deep neural networks to terminate their execution early in order to adhere to tight deadlines at the cost of accuracy.

Continue ReadingImproving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning

Freshly published: Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead

The authors are Vandana Rajan, Alessio Brutti, and Andrea Cavallaro and they will present the results in the IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP). The conference will take place in Toronto on the 06th until the 11th of June, 2021.

Continue ReadingFreshly published: Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead