Proof of Location through a Blockchain Agnostic Smart Contract Language: Design and Evaluation over Algorand and Ethereum

Le applicazioni che offrono servizi sulla base della posizione degli utenti sono sempre più utilizzate, a partire dal navigatore fino ad arrivare ai sistemi di trasporto intelligenti (ITS) i quali permetteranno ai veicoli di comunicare tra loro. Alcune di questi servizi permettono perfino di ottenere qualche incentivo se l'utente visita o passa per determinate zone. Per esempio un negozio potrebbe offrire dei coupon alle persone che si trovano nei paraggi. Tuttavia, la posizione degli utenti è facilmente falsificabile, ed in quest'ultima tipologia di servizi, essi potrebbero ottenere gli incentivi in modo illecito, raggirando il sistema. Diviene quindi necessario implementare un'architettura in grado di impedire alle persone di falsificare la loro posizione. A tal fine, numerosi lavori sono stati proposti, i quali delegherebbero la realizzazione di "prove di luogo" a dei server centralizzati oppure collocherebbero degli access point in grado di rilasciare prove o certificati a quegli utenti che si trovano vicino. In questo lavoro di tesi abbiamo ideato un'architettura diversa da quelle dei lavori correlati, cercando di utilizzare le funzionalità offerte dalla tecnologia blockchain e dalla memorizzazione distribuita. In questo modo è stato possibile progettare una soluzione che fosse decentralizzata e trasparente, assicurando l'immutabilità dei dati mediante l'utilizzo della blockchain. Inoltre, verrà dettagliato un'idea di caso d'uso da realizzare utilizzando l'architettura da noi proposta, andando ad evidenziare i vantaggi che, potenzialmente, si potrebbero trarre da essa. Infine, abbiamo implementato parte del sistema in questione, misurando i tempi ed i costi richiesti dalle transazioni su alcune delle blockchain disponibili al giorno d'oggi, utilizzando le infrastrutture messe a disposizione da Ethereum, Polygon e Algorand.

Analysis and Evaluation of Tiny Machine Learning applications

The aim of TinyML is to bring the capability of Machine Learning to ultra-low-power devices, typically under a milliwatt, and with this it breaks the traditional power barrier that prevents the widely distributed machine intelligence. TinyML allows greater reactivity and privacy by conducting inference on the computer and near-sensor while avoiding the energy cost associated with wireless communication, which is far higher at this scale than that of computing. In addition, TinyML’s efficiency makes a class of smart, battery-powered, always-on applications that can revolutionize the collection and processing of data in real time. This emerging field, which is the end of a lot of innovation, is ready to speed up its growth in the coming years. In this thesis, we deploy three model on a microcontroller. For the model, datasets are retrieved from an online repository and are preprocessed as per our requirement. The model is then trained on the split of preprocessed data at its best to get the most accuracy out of it. Later the trained model is converted to C language to make it possible to deploy on the microcontroller. Finally, we take step towards incorporating the model into the microcontroller by implementing and evaluating an interface for the user to utilize the microcontroller’s sensors. In our thesis, we will have 4 chapters. The first will give us an introduction of TinyML. The second chapter will help setup the TinyML Environment. The third chapter will be about a major use of TinyML in Wake Word Detection. The final chapter will deal with Gesture Recognition in TinyML.

Vocabulary Transfer and Knowledge Distillation for Language Model Compression

Natural Language Processing (NLP) has seen tremendous improvements over the last few years. Transformer architectures achieved impressive results in almost any NLP task, such as Text Classification, Machine Translation, and Language Generation. As time went by, transformers continued to improve thanks to larger corpora and bigger networks, reaching hundreds of billions of parameters. Training and deploying such large models has become prohibitively expensive, such that only big high tech companies can afford to train those models. Therefore, a lot of research has been dedicated to reducing a model’s size. In this thesis, we investigate the effects of Vocabulary Transfer and Knowledge Distillation for compressing large Language Models. The goal is to combine these two methodologies to further compress models without significant loss of performance. In particular, we designed different combination strategies and conducted a series of experiments on different vertical domains (medical, legal, news) and downstream tasks (Text Classification and Named Entity Recognition). Four different methods involving Vocabulary Transfer (VIPI) with and without a Masked Language Modelling (MLM) step and with and without Knowledge Distillation are compared against a baseline that assigns random vectors to new elements of the vocabulary. Results indicate that VIPI effectively transfers information of the original vocabulary and that MLM is beneficial. It is also noted that both vocabulary transfer and knowledge distillation are orthogonal to one another and may be applied jointly. The application of knowledge distillation first before subsequently applying vocabulary transfer is recommended. Finally, model performance due to vocabulary transfer does not always show a consistent trend as the vocabulary size is reduced. Hence, the choice of vocabulary size should be empirically selected by evaluation on the downstream task similar to hyperparameter tuning.

NLG-Metricverse: An End-to-End Library for Evaluating Natural Language Generation

Driven by recent deep learning breakthroughs, natural language generation (NLG) models have been at the center of steady progress in the last few years. However, since our ability to generate human-indistinguishable artificial text lags behind our capacity to assess it, it is paramount to develop and apply even better automatic evaluation metrics. To facilitate researchers to judge the effectiveness of their models broadly, we suggest NLG-Metricverse—an end-to-end open-source library for NLG evaluation based on Python. This framework provides a living collection of NLG metrics in a unified and easy- to-use environment, supplying tools to efficiently apply, analyze, compare, and visualize them. This includes (i) the extensive support of heterogeneous automatic metrics with n-arity management, (ii) the meta-evaluation upon individual performance, metric-metric and metric-human correlations, (iii) graphical interpretations for helping humans better gain score intuitions, (iv) formal categorization and convenient documentation to accelerate metrics understanding. NLG-Metricverse aims to increase the comparability and replicability of NLG research, hopefully stimulating new contributions in the area.