Network-based stochastic semisupervised learning

Semisupervised learning is a machine learning approach that is able to employ both labeled and unlabeled samples in the training process. In this paper, we propose a semisupervised data classification model based on a combined random-preferential walk of particles in a network (graph) constructed from the input dataset. The particles of the same class cooperate among themselves, while the particles of different classes compete with each other to propagate class labels to the whole network. A rigorous model definition is provided via a nonlinear stochastic dynamical system and a mathematical analysis of its behavior is carried out. A numerical validation presented in this paper confirms the theoretical predictions. An interesting feature brought by the competitive-cooperative mechanism is that the proposed model can achieve good classification rates while exhibiting low computational complexity order in comparison to other network-based semisupervised algorithms. Computer simulations conducted on synthetic and real-world datasets reveal the effectiveness of the model.

Hierarchical multi-label classification using local neural networks

Hierarchical multi-label classification is a complex classification task where the classes involved in the problem are hierarchically structured and each example may simultaneously belong to more than one class in each hierarchical level. In this paper, we extend our previous works, where we investigated a new local-based classification method that incrementally trains a multi-layer perceptron for each level of the classification hierarchy. Predictions made by a neural network in a given level are used as inputs to the neural network responsible for the prediction in the next level. We compare the proposed method with one state-of-the-art decision-tree induction method and two decision-tree induction methods, using several hierarchical multi-label classification datasets. We perform a thorough experimental analysis, showing that our method obtains competitive results to a robust global method regarding both precision and recall evaluation measures.

Machine-learning methods for structure prediction of β-barrel membrane proteins

Different types of proteins exist with diverse functions that are essential for living organisms. An important class of proteins is represented by transmembrane proteins which are specifically designed to be inserted into biological membranes and devised to perform very important functions in the cell such as cell communication and active transport across the membrane. Transmembrane β-barrels (TMBBs) are a sub-class of membrane proteins largely under-represented in structure databases because of the extreme difficulty in experimental structure determination. For this reason, computational tools that are able to predict the structure of TMBBs are needed. In this thesis, two computational problems related to TMBBs were addressed: the detection of TMBBs in large datasets of proteins and the prediction of the topology of TMBB proteins. Firstly, a method for TMBB detection was presented based on a novel neural network framework for variable-length sequence classification. The proposed approach was validated on a non-redundant dataset of proteins. Furthermore, we carried-out genome-wide detection using the entire Escherichia coli proteome. In both experiments, the method significantly outperformed other existing state-of-the-art approaches, reaching very high PPV (92%) and MCC (0.82). Secondly, a method was also introduced for TMBB topology prediction. The proposed approach is based on grammatical modelling and probabilistic discriminative models for sequence data labeling. The method was evaluated using a newly generated dataset of 38 TMBB proteins obtained from high-resolution data in the PDB. Results have shown that the model is able to correctly predict topologies of 25 out of 38 protein chains in the dataset. When tested on previously released datasets, the performances of the proposed approach were measured as comparable or superior to the current state-of-the-art of TMBB topology prediction.

Segmentazione di immagini mammografiche con convolutional neural networks

Il tumore al seno si colloca al primo posto per livello di mortalità tra le patologie tumorali che colpiscono la popolazione femminile mondiale. Diversi studi clinici hanno dimostrato come la diagnosi da parte del radiologo possa essere aiutata e migliorata dai sistemi di Computer Aided Detection (CAD). A causa della grande variabilità di forma e dimensioni delle masse tumorali e della somiglianza di queste con i tessuti che le ospitano, la loro ricerca automatizzata è un problema estremamente complicato. Un sistema di CAD è generalmente composto da due livelli di classificazione: la detection, responsabile dell’individuazione delle regioni sospette presenti sul mammogramma (ROI) e quindi dell’eliminazione preventiva delle zone non a rischio; la classificazione vera e propria (classification) delle ROI in masse e tessuto sano. Lo scopo principale di questa tesi è lo studio di nuove metodologie di detection che possano migliorare le prestazioni ottenute con le tecniche tradizionali. Si considera la detection come un problema di apprendimento supervisionato e lo si affronta mediante le Convolutional Neural Networks (CNN), un algoritmo appartenente al deep learning, nuova branca del machine learning. Le CNN si ispirano alle scoperte di Hubel e Wiesel riguardanti due tipi base di cellule identificate nella corteccia visiva dei gatti: le cellule semplici (S), che rispondono a stimoli simili ai bordi, e le cellule complesse (C) che sono localmente invarianti all’esatta posizione dello stimolo. In analogia con la corteccia visiva, le CNN utilizzano un’architettura profonda caratterizzata da strati che eseguono sulle immagini, alternativamente, operazioni di convoluzione e subsampling. Le CNN, che hanno un input bidimensionale, vengono solitamente usate per problemi di classificazione e riconoscimento automatico di immagini quali oggetti, facce e loghi o per l’analisi di documenti.

Modulation of network excitability and epileptiform activity in the hippocampus of immature rats by the activation of GlyRs

Epileptic seizures are the manifestations of epilepsy, which is a major neurological disorder and occurs with a high incidence during early childhood. A fundamental mechanism underlying epileptic seizures is loss of balance between neural excitation and inhibition toward overexcitation. Glycine receptor (GlyR) is ionotropic neurotransmitter receptor that upon binding of glycine opens an anion pore and mediates in the adult nervous system a consistent inhibitory action. While previously it was assumed that GlyRs mediate inhibition mainly in the brain stem and spinal cord, recent studies reported the abundant expression of GlyRs throughout the brain, in particular during neuronal development. But no information is available regarding whether activation of GlyRs modulates neural network excitability and epileptiform activities in the immature central nervous system (CNS). Therefore the study in this thesis addresses the role of GlyRs in the modulation of neuronal excitability and epileptiform activity in the immature rat brain. By using in vitro intact corticohippocampal formation (CHF) of rats at postnatal days 4-7 and electrophysiological methods, a series of pharmacological examinations reveal that GlyRs are directly implicated in the control of hippocampal excitation levels at this age. In this thesis I am able to show that GlyRs are functionally expressed in the immature hippocampus and exhibit the classical pharmacology of GlyR, which can be activated by both glycine and the presumed endogenous agonist taurine. This study also reveals that high concentration of taurine is anticonvulsive, but lower concentration of taurine is proconvulsive. A substantial fraction of both the pro- and anticonvulsive effects of taurine is mediated via GlyRs, although activation of GABAA receptors also considerably contributes to the taurine effects. Similarly, glycine exerts both pro- and anticonvulsive effects at low and high concentrations, respectively. The proconvulsive effects of taurine and glycine depend on NKCC1-mediated Cl- accumulation, as bath application of NKCC1 inhibitor bumetanide completely abolishes proconvulsive effects of low taurine and glycine concentrations. Inhibition of GlyRs with low concentration of strychnine triggers epileptiform activity in the CA3 region of immature CHF, indicating that intrinsically an inhibitory action of GlyRs overwhelms its depolarizing action in the immature hippocampus. Additionally, my study indicates that blocking taurine transporters to accumulate endogenous taurine reduces epileptiform activity via activation of GABAA receptors, but not GlyRs, while blocking glycine transporters has no observable effect on epileptiform activity. From the main results of this study it can be concluded that in the immature rat hippocampus, activation of GlyRs mediates both pro- and anticonvulsive effects, but that a persistent activation of GlyRs is required to prevent intrinic neuronal overexcitability. In summary, this study uncovers an important role of GlyRs in the modulation of neuronal excitability and epileptiform activity in the immature rat hippocampus, and indicates that glycinergic system can potentially be a new therapeutic target against epileptic seizures of children.

Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

Semantic memory involvement in the default mode network: a functional neuroimaging study using independent component analysis

The Default Mode Network (DMN) is a higher order functional neural network that displays activation during passive rest and deactivation during many types of cognitive tasks. Accordingly, the DMN is viewed to represent the neural correlate of internally-generated self-referential cognition. This hypothesis implies that the DMN requires the involvement of cognitive processes, like declarative memory. The present study thus examines the spatial and functional convergence of the DMN and the semantic memory system. Using an active block-design functional Magnetic Resonance Imaging (fMRI) paradigm and Independent Component Analysis (ICA), we trace the DMN and fMRI signal changes evoked by semantic, phonological and perceptual decision tasks upon visually-presented words. Our findings show less deactivation during semantic compared to the two non-semantic tasks for the entire DMN unit and within left-hemispheric DMN regions, i.e., the dorsal medial prefrontal cortex, the anterior cingulate cortex, the retrosplenial cortex, the angular gyrus, the middle temporal gyrus and the anterior temporal region, as well as the right cerebellum. These results demonstrate that well-known semantic regions are spatially and functionally involved in the DMN. The present study further supports the hypothesis of the DMN as an internal mentation system that involves declarative memory functions.

Control of recycle processes using neural networks combined with PID controller

This thesis is focused on the control of a system with recycle. A new control strategy using neural network combined with PID controller was proposed. The combined controller was studied and tested on the pressure control of a vaporizer inside a para-xylene production process. The major problems are the negative effects of recycle and the delays on instability and performance. The neural network was designed to move the process close to the set points while the PID accomplishes the finer level of disturbance rejection and offset reductions. Our simulation results show that during control, the neural network was able to determine the nonlinear relationship between steady state and manipulated variables. The results also show the disturbance rejection was handled by PID controller effectively.

Computer-aided diagnosis of carotid atherosclerosis based on ultrasound image statistics, laws' texture and neural networks

Quantitative characterisation of carotid atherosclerosis and classification into symptomatic or asymptomatic is crucial in planning optimal treatment of atheromatous plaque. The computer-aided diagnosis (CAD) system described in this paper can analyse ultrasound (US) images of carotid artery and classify them into symptomatic or asymptomatic based on their echogenicity characteristics. The CAD system consists of three modules: a) the feature extraction module, where first-order statistical (FOS) features and Laws' texture energy can be estimated, b) the dimensionality reduction module, where the number of features can be reduced using analysis of variance (ANOVA), and c) the classifier module consisting of a neural network (NN) trained by a novel hybrid method based on genetic algorithms (GAs) along with the back propagation algorithm. The hybrid method is able to select the most robust features, to adjust automatically the NN architecture and to optimise the classification performance. The performance is measured by the accuracy, sensitivity, specificity and the area under the receiver-operating characteristic (ROC) curve. The CAD design and development is based on images from 54 symptomatic and 54 asymptomatic plaques. This study demonstrates the ability of a CAD system based on US image analysis and a hybrid trained NN to identify atheromatous plaques at high risk of stroke.

Neural Networks as Cybernetic Systems - Part I

Neural Networks as Cybernetic Systems is a textbox that combines classical systems theory with artificial neural network technology.

Neural Networks as Cybernetic Systems - Part II

Neural Networks as Cybernetic Systems is a textbox that combines classical systems theory with artificial neural network technology.

Neural Networks as Cybernetic Systems (3rd and revised edition) - Part I

Neural Networks as Cybernetic Systems is a textbox that combines classical systems theory with artificial neural network technology. This third edition essentially compares with the 2nd one, but has been improved by correction of errors and by a rearrangement and minor expansion of the sections referring to recurrent networks. These changes hopefully allow for an easier comprehension of the essential aspects of this important domain that has received growing attention during the last years.

Neural Networks as Cybernetic Systems (3rd and revised edition) - Part 2

eural Networks as Cybernetic Systems is a textbox that combines classical systems theory with artificial neural network technology. This third edition essentially compares with the 2nd one, but has been improved by correction of errors and by a rearrangement and minor expansion of the sections referring to recurrent networks. These changes hopefully allow for an easier comprehension of the essential aspects of this important domain that has received growing attention during the last years.

Sensory regulation of network components underlying ciliary locomotion in Hermissenda.

Ciliary locomotion in the nudibranch mollusk Hermissenda is modulated by the visual and graviceptive systems. Components of the neural network mediating ciliary locomotion have been identified including aggregates of polysensory interneurons that receive monosynaptic input from identified photoreceptors and efferent neurons that activate cilia. Illumination produces an inhibition of type I(i) (off-cell) spike activity, excitation of type I(e) (on-cell) spike activity, decreased spike activity in type III(i) inhibitory interneurons, and increased spike activity of ciliary efferent neurons. Here we show that pairs of type I(i) interneurons and pairs of type I(e) interneurons are electrically coupled. Neither electrical coupling or synaptic connections were observed between I(e) and I(i) interneurons. Coupling is effective in synchronizing dark-adapted spontaneous firing between pairs of I(e) and pairs of I(i) interneurons. Out-of-phase burst activity, occasionally observed in dark-adapted and light-adapted pairs of I(e) and I(i) interneurons, suggests that they receive synaptic input from a common presynaptic source or sources. Rhythmic activity is typically not a characteristic of dark-adapted, light-adapted, or light-evoked firing of type I interneurons. However, burst activity in I(e) and I(i) interneurons may be elicited by electrical stimulation of pedal nerves or generated at the offset of light. Our results indicate that type I interneurons can support the generation of both rhythmic activity and changes in tonic firing depending on sensory input. This suggests that the neural network supporting ciliary locomotion may be multifunctional. However, consistent with the nonmuscular and nonrhythmic characteristics of visually modulated ciliary locomotion, type I interneurons exhibit changes in tonic activity evoked by illumination.

Serum tests, liver stiffness and artificial neural networks for diagnosing cirrhosis and portal hypertension

BACKGROUND The diagnostic performance of biochemical scores and artificial neural network models for portal hypertension and cirrhosis is not well established. AIMS To assess diagnostic accuracy of six serum scores, artificial neural networks and liver stiffness measured by transient elastography, for diagnosing cirrhosis, clinically significant portal hypertension and oesophageal varices. METHODS 202 consecutive compensated patients requiring liver biopsy and hepatic venous pressure gradient measurement were included. Several serum tests (alone and combined into scores) and liver stiffness were measured. Artificial neural networks containing or not liver stiffness as input variable were also created. RESULTS The best non-invasive method for diagnosing cirrhosis, portal hypertension and oesophageal varices was liver stiffness (C-statistics=0.93, 0.94, and 0.90, respectively). Among serum tests/scores the best for diagnosing cirrhosis and portal hypertension and oesophageal varices were, respectively, Fibrosis-4, and Lok score. Artificial neural networks including liver stiffness had high diagnostic performance for cirrhosis, portal hypertension and oesophageal varices (accuracy>80%), but were not statistically superior to liver stiffness alone. CONCLUSIONS Liver stiffness was the best non-invasive method to assess the presence of cirrhosis, portal hypertension and oesophageal varices. The use of artificial neural networks integrating different non-invasive tests did not increase the diagnostic accuracy of liver stiffness alone.