Deep Learning for Autonomous Systems and Smart Cities
MARVEL will participate in the Deep Learning for Autonomous Systems and Smart Cities summer school organized by AU from 23 to 26 May 2023.
Automatic Social Distance Estimation From Images: Performance Evaluation, Test Benchmark, and Algorithm
Detailed Info Automatic Social Distance Estimation From Images: Performance Evaluation, Test Benchmark, and Algorithm Authors:Mert Seker, Ansi Mannisto, Alexandros Iosifidis and Jenni RaitoharjuTitle:Automatic Social Distance Estimation From Images: Performance Evaluation,…
Just-in-time Decision Making with Deep Neural Networks
Almost everything we hear today about Artificial Intelligence has some connection to Deep Learning.
Dynamic hard pruning of Neural Networks at the edge of the internet
Detailed Info Dynamic hard pruning of Neural Networks at the edge of the internet Authors:Lorenzo Valerio, Franco Maria Nardini, Andrea Passarella, Raffaele PeregoTitle:Dynamic hard pruning of Neural Networks at the…
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…
Multi-Exit Vision Transformer for Dynamic Inference
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.
Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning
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.
Automated social distance estimation in smart cities using deep learning
It is without a doubt that current technologies can greatly aid the process of monitoring and ensuring the health and safety of citizens, especially when seamlessly integrated within the context of smart cities.
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.
