6,945 research outputs found
Applicazione di tecniche tomografiche a problemi di ingegneria civile. Bollettino dell'Associazione Mineraria Subalpina GEAM, Vol. 83, n.2-3, pp. 165-168
No full textTheatre as research and catalyst for health promotion
No full textIl volume, a cura di Alberto Barzanò, Cinzia Bearzot e Elisa Chiocchetti, raccoglie gli atti della Summer School del 2022 dedicata al tema “Crisi e resilienza” e contiene saggi di Elisa Chiocchetti, Estelle Cronnier, Antonio Cuciniello, Paolo De Giovanni, Roberta Ferro, Elisabetta Filippini, Laura Giovanelli, Alberto Luongo, Romina Marchisio, Tommaso Mauri, Mauro Pavesi, Carlo Perelli, Jeffrey Pufahl, Milena Raimondi, Marta Reichlin, Luca Richeldi, Franco Riva, Marco Rochini, Elena Ruzzier, Renato Sansa, Flavia Usai, Angelica Verduci, Cinzia Vicini, Luigi Weber
CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processor
Full text linkAutonomous Driving (AD) related features provide new forms of mobility that are also beneficial for other kind of intelligent and autonomous systems like robots, smart transportation, and smart industries. For these applications, the decisions need to be made fast and in real-time. Moreover, in the quest for electric mobility, this task must follow low power policy, without affecting much the autonomy of the mean of transport or the robot. These two challenges can be tackled using the emerging Spiking Neural Networks (SNNs). When deployed on a specialized neuromorphic hardware, SNNs can achieve high performance with low latency and low power consumption. In this paper, we use an SNN connected to an event-based camera for facing one of the key problems for AD, i.e., the classification between cars and other objects. To consume less power than traditional frame-based cameras, we use a Dynamic Vision Sensor (DVS) [1]. The experiments are made following an offline supervised learning rule, followed by mapping the learnt SNN model on the Intel Loihi Neuromorphic Research Chip [2]. Our best experiment achieves an accuracy on offline implementation of 86%, that drops to 83% when it is ported onto the Loihi Chip. The Neuromorphic Hardware implementation has maximum 0.72 ms of latency for every sample, and consumes only 310 mW. To the best of our knowledge, this work is the first implementation of an event-based car classifier on a Neuromorphic Chip
LaneSNNs: Spiking Neural Networks for Lane Detection on the Loihi Neuromorphic Processor
Full text linkAutonomous Driving (AD) related features represent important elements for the next generation of mobile robots and autonomous vehicles focused on increasingly intelligent, autonomous, and interconnected systems. The applications involving the use of these features must provide, by definition, real-time decisions, and this property is key to avoid catastrophic accidents. Moreover, all the decision processes must require low power consumption, to increase the lifetime and autonomy of battery-driven systems. These challenges can be addressed through efficient implementations of Spiking Neural Networks (SNNs) on Neuromorphic Chips and the use of event-based cameras instead of traditional frame-based cameras.In this paper, we present a new SNN-based approach, called LaneSNN, for detecting the lanes marked on the streets using the event-based camera input. We develop four novel SNN models characterized by low complexity and fast response, and train them using an offline supervised learning rule. Afterward, we implement and map the learned SNNs models onto the Intel Loihi Neuromorphic Research Chip. For the loss function, we develop a novel method based on the linear composition of Weighted binary Cross Entropy (WCE) and Mean Squared Error (MSE) measures. Our experimental results show a maximum Intersection over Union (IoU) measure of about 0.62 and very low power consumption of about 1 W. The best IoU is achieved with an SNN implementation that occupies only 36 neurocores on the Loihi processor while providing a low latency of less than 8 ms to recognize an image, thereby enabling real-time performance. The IoU measures provided by our networks are comparable with the state-of-the-art, but at a much low power consumption of 1 W
[Poesia] Três poemas de Alberto Secama
No full textThree poems by Alberto Secama. About the author: Alberto Secama is an Angolan poet who has poems published on many websites and on facebook:https://www.facebook.com/Xungurra/abouthttp://www.pordentrodaafrica.com/cultura/africa-em-verso-rio-kwanza-por-alberto-secamahttp://www.pordentrodaafrica.com/cultura/africa-em-verso-zong-por-alberto-secamahttp://www.pordentrodaafrica.com/cultura/coluna-africa-em-verso-o-sol-la-fora-por-alberto-secamaTres poemas de Alberto Secama. Sobre el autor: Alberto Secama es un poeta angoleño que tiene poemas publicados en varios sitios y en el facebook:https://www.facebook.com/Xungurra/abouthttp://www.pordentrodaafrica.com/cultura/africa-em-verso-rio-kwanza-por-alberto-secamahttp://www.pordentrodaafrica.com/cultura/africa-em-verso-zong-por-alberto-secamahttp://www.pordentrodaafrica.com/cultura/coluna-africa-em-verso-o-sol-la-fora-por-alberto-secamaTrês poemas de Alberto Secama. Sobre o autor: Alberto Secama é um poeta angolano que possui poemas publicados em vários sites e no facebook:https://www.facebook.com/Xungurra/abouthttp://www.pordentrodaafrica.com/cultura/africa-em-verso-rio-kwanza-por-alberto-secamahttp://www.pordentrodaafrica.com/cultura/africa-em-verso-zong-por-alberto-secamahttp://www.pordentrodaafrica.com/cultura/coluna-africa-em-verso-o-sol-la-fora-por-alberto-secam
An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor
Full text linkSpiking Neural Networks (SNNs), the third generation NNs, have come under the spotlight for machine learning based applications due to their biological plausibility and reduced complexity compared to traditional artificial Deep Neural Networks (DNNs). These SNNs can be implemented with extreme energy efficiency on neuromorphic processors like the Intel Loihi research chip, and fed by event-based sensors, such as DVS cameras. However, DNNs with many layers can achieve relatively high accuracy on image classification and recognition tasks, as the research on learning rules for SNNs for real-world applications is still not mature. The accuracy results for SNNs are typically obtained either by converting the trained DNNs into SNNs, or by directly designing and training SNNs in the spiking domain. Towards the conversion from a DNN to an SNN, we perform a comprehensive analysis of such process, specifically designed for Intel Loihi, showing our methodology for the design of an SNN that achieves nearly the same accuracy results as its corresponding DNN. Towards the usage of the event-based sensors, we design a pre-processing method, evaluated for the DvsGesture dataset, which makes it possible to be used in the DNN domain. Hence, based on the outcome of the first analysis, we train a DNN for the pre-processed DvsGesture dataset, and convert it into the spike domain for its deployment on Intel Loihi, which enables real-time gesture recognition. The results show that our SNN achieves 89.64% classification accuracy and occupies only 37 Loihi cores
Orizzonti mantovani. Spunti e dinamiche paesaggistiche ne L'Illustrissimo di Alberto Cantoni
Full text linkIn the literary production of Alberto Cantoni, short story writer and novelist between the nineteenth and twentieth centuries, the novel L'Illustrissimo is highly important both because it is the last publication of the author, from Pomponesco, a small town a few kilometers south of Mantua, both because it summarizes in a single text the different nuances and different directions that his writing has taken over the course of his literary career, also due to a writing and processing time that embraces the entire span of years of his career itself. In the foreground, in addition to the numerous and brilliant characters, one of the protagonists is the Mantuan landscape which, not a simple background, becomes a true literary parameter which in different and significant ways affects the purposes and mechanisms of the novel
Giardini e Paradisi
No full textUn giardino può esistere non tanto per quello che vuole essere (o meglio apparire), ma soprattutto per quello che deve significare in un contesto ben preciso, finalizzato ad un'utenza ben definita. Il contributo descrive i diversi sensi del giardino:senso ambientale, vegetale ed architettonico, offrendo una panoramica sull'attuale significato dei giardini
PruNet: Class-Blind Pruning Method For Deep Neural Networks
Full text linkDNNs are highly memory and computationally
intensive, due to which they are unfeasible to deploy in real time
or mobile applications, where power and memory resources are
scarce. Introducing sparsity in the network is a way to reduce
those requirements. However, systematically employing pruning
under given accuracy requirements is a challenging problem.
We propose a novel methodology that iteratively applies a
magnitude-based Class-Blind pruning to compress a DNN for
obtaining a sparse model. It is a generic methodology and can
be applied to different types of DNNs. We demonstrate that
retraining after pruning is essential to restore the accuracy of
the network. Experimental results show that our methodology
is able to reduce the model size by around two orders of
magnitude, without noticeably affecting the accuracy. It requires
several iterations of pruning and retraining, but can achieve up
to 190x Memory Saving Ratio (for the LeNet on the MNIST
dataset) when compared to the baseline model. Similar results
are also obtained for more complex networks like 91x for
VGG-16 on the CIFAR100 dataset. If we combine this work
with an efficient coding for sparse networks, like Compressed
Sparse Column (CSC) or Compressed Sparse Row (CSR), we
can obtain a reduced memory footprint. Our methodology can
be complemented by other compression techniques, like weight
sharing, quantization or fixed-point conversion, that allows to
further reduce memory and computations
R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensors
Full text linkSpiking Neural Networks (SNNs) aim at providing energy-efficient learning capabilities when implemented on neuromorphic chips with event-based Dynamic Vision Sensors (DVS). This paper studies the robustness of SNNs against adversarial attacks on such DVS-based systems, and proposes R-SNN, a novel methodology for robustifying SNNs through efficient DVS-noise filtering. We are the first to generate adversarial attacks on DVS signals (i.e., frames of events in the spatio-temporal domain) and to apply noise filters for DVS sensors in the quest for defending against adversarial attacks. Our results show that the noise filters effectively prevent the SNNs from being fooled. The SNNs in our experiments provide more than 90% accuracy on the DVS-Gesture and NMNIST datasets under different adversarial threat models
- …
