Learning user and product distributed representations using a sequence model for sentiment analysis

In product reviews, it is observed that the distribution of polarity ratings over reviews written by different users or evaluated based on different products are often skewed in the real world. As such, incorporating user and product information would be helpful for the task of sentiment classification of reviews. However, existing approaches ignored the temporal nature of reviews posted by the same user or evaluated on the same product. We argue that the temporal relations of reviews might be potentially useful for learning user and product embedding and thus propose employing a sequence model to embed these temporal relations into user and product representations so as to improve the performance of document-level sentiment analysis. Specifically, we first learn a distributed representation of each review by a one-dimensional convolutional neural network. Then, taking these representations as pretrained vectors, we use a recurrent neural network with gated recurrent units to learn distributed representations of users and products. Finally, we feed the user, product and review representations into a machine learning classifier for sentiment classification. Our approach has been evaluated on three large-scale review datasets from the IMDB and Yelp. Experimental results show that: (1) sequence modeling for the purposes of distributed user and product representation learning can improve the performance of document-level sentiment classification; (2) the proposed approach achieves state-of-The-Art results on these benchmark datasets.

Efficient Image and Video Representations for Retrieval

Image (Video) retrieval is an interesting problem of retrieving images (videos) similar to the query. Images (Videos) are represented in an input (feature) space and similar images (videos) are obtained by finding nearest neighbors in the input representation space. Numerous input representations both in real valued and binary space have been proposed for conducting faster retrieval. In this thesis, we present techniques that obtain improved input representations for retrieval in both supervised and unsupervised settings for images and videos. Supervised retrieval is a well known problem of retrieving same class images of the query. We address the practical aspects of achieving faster retrieval with binary codes as input representations for the supervised setting in the first part, where binary codes are used as addresses into hash tables. In practice, using binary codes as addresses does not guarantee fast retrieval, as similar images are not mapped to the same binary code (address). We address this problem by presenting an efficient supervised hashing (binary encoding) method that aims to explicitly map all the images of the same class ideally to a unique binary code. We refer to the binary codes of the images as `Semantic Binary Codes' and the unique code for all same class images as `Class Binary Code'. We also propose a new class­ based Hamming metric that dramatically reduces the retrieval times for larger databases, where only hamming distance is computed to the class binary codes. We also propose a Deep semantic binary code model, by replacing the output layer of a popular convolutional Neural Network (AlexNet) with the class binary codes and show that the hashing functions learned in this way outperforms the state­ of ­the art, and at the same time provide fast retrieval times. In the second part, we also address the problem of supervised retrieval by taking into account the relationship between classes. For a given query image, we want to retrieve images that preserve the relative order i.e. we want to retrieve all same class images first and then, the related classes images before different class images. We learn such relationship aware binary codes by minimizing the similarity between inner product of the binary codes and the similarity between the classes. We calculate the similarity between classes using output embedding vectors, which are vector representations of classes. Our method deviates from the other supervised binary encoding schemes as it is the first to use output embeddings for learning hashing functions. We also introduce new performance metrics that take into account the related class retrieval results and show significant gains over the state­ of­ the art. High Dimensional descriptors like Fisher Vectors or Vector of Locally Aggregated Descriptors have shown to improve the performance of many computer vision applications including retrieval. In the third part, we will discuss an unsupervised technique for compressing high dimensional vectors into high dimensional binary codes, to reduce storage complexity. In this approach, we deviate from adopting traditional hyperplane hashing functions and instead learn hyperspherical hashing functions. The proposed method overcomes the computational challenges of directly applying the spherical hashing algorithm that is intractable for compressing high dimensional vectors. A practical hierarchical model that utilizes divide and conquer techniques using the Random Select and Adjust (RSA) procedure to compress such high dimensional vectors is presented. We show that our proposed high dimensional binary codes outperform the binary codes obtained using traditional hyperplane methods for higher compression ratios. In the last part of the thesis, we propose a retrieval based solution to the Zero shot event classification problem - a setting where no training videos are available for the event. To do this, we learn a generic set of concept detectors and represent both videos and query events in the concept space. We then compute similarity between the query event and the video in the concept space and videos similar to the query event are classified as the videos belonging to the event. We show that we significantly boost the performance using concept features from other modalities.

Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN

Different types of sentences express sentiment in very different ways. Traditional sentence-level sentiment classification research focuses on one-technique-fits-all solution or only centers on one special type of sentences. In this paper, we propose a divide-and-conquer approach which first classifies sentences into different types, then performs sentiment analysis separately on sentences from each type. Specifically, we find that sentences tend to be more complex if they contain more sentiment targets. Thus, we propose to first apply a neural network based sequence model to classify opinionated sentences into three types according to the number of targets appeared in a sentence. Each group of sentences is then fed into a one-dimensional convolutional neural network separately for sentiment classification. Our approach has been evaluated on four sentiment classification datasets and compared with a wide range of baselines. Experimental results show that: (1) sentence type classification can improve the performance of sentence-level sentiment analysis; (2) the proposed approach achieves state-of-the-art results on several benchmarking datasets.

Intersubjectivity and sentiment:from language to knowledge

Intersubjectivity is an important concept in psychology and sociology. It refers to sharing conceptualizations through social interactions in a community and using such shared conceptualization as a resource to interpret things that happen in everyday life. In this work, we make use of intersubjectivity as the basis to model shared stance and subjectivity for sentiment analysis. We construct an intersubjectivity network which links review writers, terms they used, as well as the polarities of the terms. Based on this network model, we propose a method to learn writer embeddings which are subsequently incorporated into a convolutional neural network for sentiment analysis. Evaluations on the IMDB, Yelp 2013 and Yelp 2014 datasets show that the proposed approach has achieved the state-of-the-art performance.

Classificazione di Radiografie Toraciche per la Diagnosi del COVID-19 con Reti Convoluzionali e Vision Transformer

Negli ultimi due anni, per via della pandemia generata dal virus Covid19, la vita in ogni angolo del nostro pianeta è drasticamente cambiata. Ad oggi, nel mondo, sono oltre duecentoventi milioni le persone che hanno contratto questo virus e sono quasi cinque milioni le persone decedute. In alcuni periodi si è arrivati ad avere anche un milione di nuovi contagiati al giorno e mediamente, negli ultimi sei mesi, questo dato è stato di più di mezzo milione al giorno. Gli ospedali, soprattutto nei paesi meno sviluppati, hanno subito un grande stress e molte volte hanno avuto una carenza di risorse per fronteggiare questa grave pandemia. Per questo motivo ogni ricerca in questo campo diventa estremamente importante, soprattutto quelle che, con l'ausilio dell'intelligenza artificiale, riescono a dare supporto ai medici. Queste tecnologie una volta sviluppate e approvate possono essere diffuse a costi molto bassi e accessibili a tutti. In questo elaborato sono stati sperimentati e valutati due diversi approcci alla diagnosi del Covid-19 a partire dalle radiografie toraciche dei pazienti: il primo metodo si basa sul transfer learning di una rete convoluzionale inizialmente pensata per la classificazione di immagini. Il secondo approccio utilizza i Vision Transformer (ViT), un'architettura ampiamente diffusa nel campo del Natural Language Processing adattata ai task di Visione Artificiale. La prima soluzione ha ottenuto un’accuratezza di 0.85 mentre la seconda di 0.92, questi risultati, soprattutto il secondo, sono molto incoraggianti soprattutto vista la minima quantità di dati di training necessaria.

Deep Learning Architectures for time of arrival detection in Acoustic Emissions Monitoring

Acoustic Emission (AE) monitoring can be used to detect the presence of damage as well as determine its location in Structural Health Monitoring (SHM) applications. Information on the time difference of the signal generated by the damage event arriving at different sensors is essential in performing localization. This makes the time of arrival (ToA) an important piece of information to retrieve from the AE signal. Generally, this is determined using statistical methods such as the Akaike Information Criterion (AIC) which is particularly prone to errors in the presence of noise. And given that the structures of interest are surrounded with harsh environments, a way to accurately estimate the arrival time in such noisy scenarios is of particular interest. In this work, two new methods are presented to estimate the arrival times of AE signals which are based on Machine Learning. Inspired by great results in the field, two models are presented which are Deep Learning models - a subset of machine learning. They are based on Convolutional Neural Network (CNN) and Capsule Neural Network (CapsNet). The primary advantage of such models is that they do not require the user to pre-define selected features but only require raw data to be given and the models establish non-linear relationships between the inputs and outputs. The performance of the models is evaluated using AE signals generated by a custom ray-tracing algorithm by propagating them on an aluminium plate and compared to AIC. It was found that the relative error in estimation on the test set was < 5% for the models compared to around 45% of AIC. The testing process was further continued by preparing an experimental setup and acquiring real AE signals to test on. Similar performances were observed where the two models not only outperform AIC by more than a magnitude in their average errors but also they were shown to be a lot more robust as compared to AIC which fails in the presence of noise.

Design, development and guidance of the Airborne’s quadrotor

The main goal of the Airborne project is to develop, at technology readiness level 8 (TRL8), a few selected robotic aerial technologies for quick localization of victims by avalanches by equipping drones with two forefront sensors used in SAR operations in case of avalanches, namely the ARVA and RECCO. This thesis focuses on the design, development, and guidance of the TRL8 quadrotor developed during the project. We present and describe the design method that allowed us to obtain an EMI shielded UAV capable of integrating both RECCO and ARVA sensors. Besides, is presented the avionics and power train design and building procedure in order to obtain a modular UAV frame that can be easily carried by rescuers and achieves all the performance benchmarks of the project. Additionally, in addition to the onboard algorithms, a multivariate regressive convolutional neural network whose goal is the localization of the ARVA signal is presented. On guidance, the automatic flight procedure is described, and the onboard waypoint generator algorithm is presented. The goal of this algorithm is the generation and execution of an automatic grid pattern without the need to know the map in advance and without the support of a control ground station (CGS). Moreover, we present an iterative trajectory planner that does not need pre-knowledge of the map and uses Bézier curves to address optimal, dynamically feasible, safe, and re-plannable trajectories. The goal is to develop a method that allows local and fast replannings in case of an obstacle pop up or if some waypoints change. This makes the novel planner suitable to be applied in SAR operations. The introduction of the final version of the quadrotor is supported by internal flight tests and field tests performed in real operative scenarios by the Club Alpino Italiano (CAI).

Supervised and weakly supervised counting-by-segmentation: the fluorescent microscopy use case

This thesis focuses on automating the time-consuming task of manually counting activated neurons in fluorescent microscopy images, which is used to study the mechanisms underlying torpor. The traditional method of manual annotation can introduce bias and delay the outcome of experiments, so the author investigates a deep-learning-based procedure to automatize this task. The author explores two of the main convolutional-neural-network (CNNs) state-of-the-art architectures: UNet and ResUnet family model, and uses a counting-by-segmentation strategy to provide a justification of the objects considered during the counting process. The author also explores a weakly-supervised learning strategy that exploits only dot annotations. The author quantifies the advantages in terms of data reduction and counting performance boost obtainable with a transfer-learning approach and, specifically, a fine-tuning procedure. The author released the dataset used for the supervised use case and all the pre-training models, and designed a web application to share both the counting process pipeline developed in this work and the models pre-trained on the dataset analyzed in this work.

Machine Learning in Applicazione alla Prevenzione del Morbo di Alzheimer

Il morbo di Alzheimer è ancora una malattia incurabile. Negli ultimi anni l'aumento progressivo dell'aspettativa di vita ha contribuito a un'insorgenza maggiore di questa patologia, specialmente negli stati con l'età media più alta, tra cui l'Italia. La prevenzione risulta una delle poche vie con cui è possibile arginarne lo sviluppo, ed in questo testo vengono analizzate le potenzialità di alcune tecniche di Machine Learning atte alla creazione di modelli di supporto diagnostico per Alzheimer. Dopo un'opportuna introduzione al morbo di Alzheimer ed al funzionamento generale del Machine Learning, vengono presentate e approfondite due delle tecniche più promettenti per la diagnosi di patologie neurologiche, ovvero la Support Vector Machine (macchina a supporto vettoriale, SVM) e la Convolutional Neural Network (rete neurale convoluzionale, CNN), con annessi risultati, punti di forza e principali debolezze. La conclusione verterà sul possibile futuro delle intelligenze artificiali, con particolare attenzione all'ambito sanitario, e verranno discusse le principali difficoltà nelle quali queste incombono prima di essere commercializzate, insieme a plausibili soluzioni.

Application of active and transfer learning to wound image segmentation

Wound management is a fundamental task in standard clinical practice. Automated solutions already exist for humans, but there is a lack of applications on wound management for pets. The importance of a precise and efficient wound assessment is helpful to improve diagnosis and to increase the effectiveness of treatment plans for the chronic wounds. The goal of the research was to propose an automated pipeline capable of segmenting natural light-reflected wound images of animals. Two datasets composed by light-reflected images were used in this work: Deepskin dataset, 1564 human wound images obtained during routine dermatological exams, with 145 manual annotated images; Petwound dataset, a set of 290 wound photos of dogs and cats with 0 annotated images. Two implementations of U-Net Convolutioal Neural Network model were proposed for the automated segmentation. Active Semi-Supervised Learning techniques were applied for human-wound images to perform segmentation from 10% of annotated images. Then the same models were trained, via Transfer Learning, adopting an Active Semi- upervised Learning to unlabelled animal-wound images. The combination of the two training strategies proved their effectiveness in generating large amounts of annotated samples (94% of Deepskin, 80% of PetWound) with the minimal human intervention. The correctness of automated segmentation were evaluated by clinical experts at each round of training thus we can assert that the results obtained in this thesis stands as a reliable solution to perform a correct wound image segmentation. The use of Transfer Learning and Active Semi-Supervied Learning allows to minimize labelling effort from clinicians, even requiring no starting manual annotation at all. Moreover the performances of the model with limited number of parameters suggest the implementation of smartphone-based application to this topic, helping the future standardization of light-reflected images as acknowledge medical images.

Generazione di osservabili radiometriche per navigazione deep space tramite reti neurali convoluzionali

Grazie all’evoluzione degli strumenti di calcolo e delle strutture digitali, le intelligenze artificiali si sono evolute considerevolmente negli ultimi anni, permettendone sempre nuove e complesse applicazioni. L’interesse del presente progetto di tesi è quello di creare un modello di studio preliminare di intelligenza artificiale definita come Rete Neurale Convoluzionale, o Convolutional Neural Network (CNN), al fine di essere impiegata nel campo della radioscienza e dell’esplorazione planetaria. In particolare, uno degli interessi principali di applicazione del modello è negli studi di geodesia compiuti tramite determinazione orbitale di satelliti artificiali nel loro moto attorno ai corpi celesti. Le accelerazioni causate dai campi gravitazionali planetari perturbano le orbite dei satelliti artificiali, queste variazioni vengono captate dai ricevitori radio a terra sottoforma di shift Doppler della frequenza del segnale, a partire dalla quale è quindi possibile determinare informazioni dettagliate sul campo di gravità e sulla struttura interna del corpo celeste in esame. Per poter fare ciò, occorre riuscire a determinare l’esatta frequenza del segnale in arrivo, il quale, per via di perdite e disturbi durante il suo tragitto, presenterà sempre una componente di rumore. Il metodo più comune per scindere la componente di informazione da quella di rumore e ricavarne la frequenza effettiva è l’applicazione di trasformate di Fourier a tempo breve, o Short-time Fourier Transform (STFT). Con l’attività sperimentale proposta, ci si è quindi posto l’obiettivo di istruire un CNN alla stima della frequenza di segnali reali sinusoidali rumorosi per avere un modello computazionalmente rapido e affidabile a supporto delle operazioni di pre-processing per missioni di radio-scienza.

Continual learning on nano drones

Miniaturized flying robotic platforms, called nano-drones, have the potential to revolutionize the autonomous robots industry sector thanks to their very small form factor. The nano-drones’ limited payload only allows for a sub-100mW microcontroller unit for the on-board computations. Therefore, traditional computer vision and control algorithms are too computationally expensive to be executed on board these palm-sized robots, and we are forced to rely on artificial intelligence to trade off accuracy in favor of lightweight pipelines for autonomous tasks. However, relying on deep learning exposes us to the problem of generalization since the deployment scenario of a convolutional neural network (CNN) is often composed by different visual cues and different features from those learned during training, leading to poor inference performances. Our objective is to develop and deploy and adaptation algorithm, based on the concept of latent replays, that would allow us to fine-tune a CNN to work in new and diverse deployment scenarios. To do so we start from an existing model for visual human pose estimation, called PULPFrontnet, which is used to identify the pose of a human subject in space through its 4 output variables, and we present the design of our novel adaptation algorithm, which features automatic data gathering and labeling and on-device deployment. We therefore showcase the ability of our algorithm to adapt PULP-Frontnet to new deployment scenarios, improving the R2 scores of the four network outputs, with respect to an unknown environment, from approximately [−0.2, 0.4, 0.0,−0.7] to [0.25, 0.45, 0.2, 0.1]. Finally we demonstrate how it is possible to fine-tune our neural network in real time (i.e., under 76 seconds), using the target parallel ultra-low power GAP 8 System-on-Chip on board the nano-drone, and we show how all adaptation operations can take place using less than 2mWh of energy, a small fraction of the available battery power.

Robotic grasping: State of the art and modular real-world implementation

Robotic Grasping is an important research topic in robotics since for robots to attain more general-purpose utility, grasping is a necessary skill, but very challenging to master. In general the robots may use their perception abilities like an image from a camera to identify grasps for a given object usually unknown. A grasp describes how a robotic end-effector need to be positioned to securely grab an object and successfully lift it without lost it, at the moment state of the arts solutions are still far behind humans. In the last 5–10 years, deep learning methods take the scene to overcome classical problem like the arduous and time-consuming approach to form a task-specific algorithm analytically. In this thesis are present the progress and the approaches in the robotic grasping field and the potential of the deep learning methods in robotic grasping. Based on that, an implementation of a Convolutional Neural Network (CNN) as a starting point for generation of a grasp pose from camera view has been implemented inside a ROS environment. The developed technologies have been integrated into a pick-and-place application for a Panda robot from Franka Emika. The application includes various features related to object detection and selection. Additionally, the features have been kept as generic as possible to allow for easy replacement or removal if needed, without losing time for improvement or new testing.

Training deep convolutional architectures for vision

Les tâches de vision artificielle telles que la reconnaissance d’objets demeurent irrésolues à ce jour. Les algorithmes d’apprentissage tels que les Réseaux de Neurones Artificiels (RNA), représentent une approche prometteuse permettant d’apprendre des caractéristiques utiles pour ces tâches. Ce processus d’optimisation est néanmoins difficile. Les réseaux profonds à base de Machine de Boltzmann Restreintes (RBM) ont récemment été proposés afin de guider l’extraction de représentations intermédiaires, grâce à un algorithme d’apprentissage non-supervisé. Ce mémoire présente, par l’entremise de trois articles, des contributions à ce domaine de recherche. Le premier article traite de la RBM convolutionelle. L’usage de champs réceptifs locaux ainsi que le regroupement d’unités cachées en couches partageant les même paramètres, réduit considérablement le nombre de paramètres à apprendre et engendre des détecteurs de caractéristiques locaux et équivariant aux translations. Ceci mène à des modèles ayant une meilleure vraisemblance, comparativement aux RBMs entraînées sur des segments d’images. Le deuxième article est motivé par des découvertes récentes en neurosciences. Il analyse l’impact d’unités quadratiques sur des tâches de classification visuelles, ainsi que celui d’une nouvelle fonction d’activation. Nous observons que les RNAs à base d’unités quadratiques utilisant la fonction softsign, donnent de meilleures performances de généralisation. Le dernière article quand à lui, offre une vision critique des algorithmes populaires d’entraînement de RBMs. Nous montrons que l’algorithme de Divergence Contrastive (CD) et la CD Persistente ne sont pas robustes : tous deux nécessitent une surface d’énergie relativement plate afin que leur chaîne négative puisse mixer. La PCD à "poids rapides" contourne ce problème en perturbant légèrement le modèle, cependant, ceci génère des échantillons bruités. L’usage de chaînes tempérées dans la phase négative est une façon robuste d’adresser ces problèmes et mène à de meilleurs modèles génératifs.

Detecção de refletores sísmicos por rede neural discreta

As redes neurais artificiais têm provado serem uma poderosa técnica na resolução de uma grande variedade de problemas de otimização. Nesta dissertação é desenvolvida uma nova rede neural, tipo recorrente, sem realimentação (self-feedback loops) e sem neurônios ocultos, para o processamento do sinal sísmico, para fornecer a posição temporal, a polaridade e as amplitudes estimadas dos refletores sísmicos, representadas pelos seus coeficientes de reflexão. A principal característica dessa nova rede neural consiste no tipo de função de ativação utilizada, a qual permite três possíveis estados para o neurônio. Busca-se estimar a posição dos refletores sísmicos e reproduzir as verdadeiras polaridades desses refletores. A idéia básica desse novo tipo de rede, aqui denominada rede neural discreta (RND), é relacionar uma função objeto, que descreve o problema geofísico, com a função de Liapunov, que descreve a dinâmica da rede neural. Deste modo, a dinâmica da rede leva a uma minimização local da sua função de Liapunov e consequentemente leva a uma minimização da função objeto. Assim, com uma codificação conveniente do sinal de saída da rede tem-se uma solução do problema geofísico. A avaliação operacional da arquitetura desta rede neural artificial é realizada em dados sintéticos gerados através do modelo convolucional simples e da teoria do raio. A razão é para explicar o comportamento da rede com dados contaminados por ruído, e diante de pulsos fonte de fases mínima, máxima e misturada.