1,721,052 research outputs found
Neuromodulation and neural circuit performativity: Adequacy conditions for their computational modelling
No full textAn understanding of the functional repertoire of neural circuits and their plasticity requires knowledge of neural connectivity diagrams and their dynamical evolution. However, one must additionally take into account the fast and reversible functional effects induced by neuromodulatory mechanisms which do not alter neural circuit diagrams. Neuromodulators contribute crucially to determine the performativity of a neural circuit, that is, its ability to change behavior, and especially behavioral changes occurring under temporal constraints that are incompatible with the longer time scales of Hebbian learning and other forms of neural learning. This paper focuses on two properties of neuromodulatory action that have been relatively neglected so far. These properties are the functional soundness of neuromodulated circuits and the robustness of neuromodulatory action. Both properties are analyzed here as sources of functional specifications for the computational modeling of neural circuit performativity. In particular, taking dynamical systems that are based on CTRNNs (Continuous Time Recurrent Neural Networks) as an exemplary class of computational models, it is argued that robustness is suitably modeled there by means of a hysteresis process, and functional soundness by means of a multiplicity of stable fixed points
A simple and efficient architecture for trainable activation functions
No full textAutomatically learning the best activation function for the task is an active topic in neural network research. At the moment, despite promising results, it is still challenging to determine a method for learning an activation function that is, at the same time, theoretically simple and easy to implement. Moreover, most of the methods proposed so far introduce new parameters or adopt different learning techniques. In this work, we propose a simple method to obtain a trained activation function which adds to the neural network local sub-networks with a small number of neurons. Experiments show that this approach could lead to better results than using a pre-defined activation function, without introducing the need to learn a large number of additional parameters
XAI approach for addressing the dataset shift problem: BCI as a case study
No full textIn the Machine Learning (ML) literature, a well-known problem is the Dataset Shift problem where, differently from the ML standard hypothesis, the data in the training and test sets can follow different probability distributions leading ML systems toward poor generalisation performances. Therefore, such systems can be unreliable and risky, particularly when used in safety-critical domains. This problem is intensely felt in the Brain-Computer Interface (BCI) context, where bio-signals as Electroencephalographic (EEG) are used. In fact, EEG signals are highly non-stationary signals both over time and between different subjects. Despite several efforts in developing BCI systems to deal with different acquisition times or subjects, performance in many BCI applications remains low. Exploiting the knowledge from eXplainable Artificial Intelligence (XAI) methods can help develop EEG-based AI approaches, overcoming the performance returned by the current ones. The proposed framework will give greater robustness and reliability to BCI systems with respect to the current state of the art, alleviating the dataset shift problem and allowing a BCI system to be used by different subjects at different times without the need for further calibration/training stages
XAI approach for addressing the dataset shift problem: BCI as a case study
Full text linkIn the Machine Learning (ML) literature, a well-known problem is the Dataset Shift problem where, differently from the ML standard hypothesis, the data in the training and test sets can follow different probability distributions leading ML systems toward poor generalisation performances. Therefore, such systems can be unreliable and risky, particularly when used in safety-critical domains. This problem is intensely felt in the Brain-Computer Interface (BCI) context, where bio-signals as Electroencephalographic (EEG) are used. In fact, EEG signals are highly non-stationary signals both over time and between different subjects. Despite several efforts in developing BCI systems to deal with different acquisition times or subjects, performance in many BCI applications remains low. Exploiting the knowledge from eXplainable Artificial Intelligence (XAI) methods can help develop EEG-based AI approaches, overcoming the performance returned by the current ones. The proposed framework will give greater robustness and reliability to BCI systems with respect to the current state of the art, alleviating the dataset shift problem and allowing a BCI system to be used by different subjects at different times without the need for further calibration/training stages
Dynamic Local Filters in Graph Convolutional Neural Networks
No full textOver the last few years, we have seen increasing data generated from non-Euclidean domains, usually represented as graphs with complex relationships. Graph Neural Networks (GNN) have gained a high interest because of their potential in processing graph-structured data. In particular, there is a strong interest in performing convolution on graphs using specific GNN architectures, generally called Graph Convolutional Neural Networks (GCNN). This paper presents a novel method to adapt the behaviour of a GCNN using an input-based dynamically generated filter. Notice that the idea of adapting the network behaviour to the inputs they process to maximize the total performances has aroused much interest in the neural networks literature over the years. The experimental assessment confirms the capabilities of the proposed approach, achieving promising results using simple architectures with a low number of filters
Improving the Performance of Already Trained Classifiers Through an Automatic Explanation-Based Learning Approach
No full textWhile much of the existing XAI literature focuses on explaining AI systems, there has recently been a growing interest in using XAI techniques to improve the performance of AI systems without human involvement. In this context, we propose a novel explanation-based learning approach that aims to improve the performance of an already trained Deep-Learning (DL) classifier M without the need for extensive retraining. Our approach involves augmenting the responses of M with specific and relevant features obtained from a predictor P of explanations, which is trained to highlight relevant information in terms of input encoded features. These encoded features, together with the responses provided by M, are then fed into an additional simple classifier to produce a new classification. Importantly, P is constructed so that its training is less computationally expensive than training M from scratch, or equivalent to fine-tuning M. This approach avoids the computational cost associated with training a complex DL model from scratch. To evaluate our proposal, we used 1) three different well-known DL models as M, specifically EfficientNet-B2, MobileNet, LeNet-5, and 2) three standard image datasets, specifically CIFAR-10, CIFAR-100 and STL-10. The results show that our approach uniformly improves the performance of all already trained DL models for all the inspected datasets
Middle-Level Features for the Explanation of Classification Systems by Sparse Dictionary Methods
Full text linkMachine learning (ML) systems are affected by a pervasive lack of transparency. The eXplainable Artificial Intelligence (XAI) research area addresses this problem and the related issue of explaining the behavior of ML systems in terms that are understandable to human beings. In many explanation of XAI approaches, the output of ML systems are explained in terms of low-level features of their inputs. However, these approaches leave a substantive explanatory burden with human users, insofar as the latter are required to map low-level properties into more salient and readily understandable parts of the input. To alleviate this cognitive burden, an alternative model-agnostic framework is proposed here. This framework is instantiated to address explanation problems in the context of ML image classification systems, without relying on pixel relevance maps and other low-level features of the input. More specifically, one obtains sets of middle-level properties of classification inputs that are perceptually salient by applying sparse dictionary learning techniques. These middle-level properties are used as building blocks for explanations of image classifications. The achieved explanations are parsimonious, for their reliance on a limited set of middle-level image properties. And they can be contrastive, because the set of middle-level image properties can be used to explain why the system advanced the proposed classification over other antagonist classifications. In view of its model-agnostic character, the proposed framework is adaptable to a variety of other ML systems and explanation problems
Machine learning-based heating detection from pressure measurements in the CERN Large Hadron Collider
No full textMachine learning models are proposed to successfully detect heating from pressure measurements in synchrotron colliders. These models allow to analyze all the pressure measurements in the time available between two consecutive machine runs. The limits of simple heuristic-based algorithms arsing from noise and non-reproducibility are overcome by the proposed machine learning models. These models were trained, tested, and compared with an heuristic-based base-line approach. In particular, for the case of the CERN Large Hadron Collider (LHC), they reached better performance than base-line algorithms, both in precision and recall scores
Toward the application of XAI methods in EEG-based systems
Full text linkAn interesting case of the well-known Dataset Shift Problem is the classification of Electroencephalogram (EEG) signals in the context of Brain-Computer Interface (BCI). The non-stationarity of EEG signals can lead to poor generalisation performance in BCI classification systems used in different sessions, also from the same subject. In this paper, we start from the hypothesis that the Dataset Shift problem can be alleviated by exploiting suitable eXplainable Artificial Intelligence (XAI) methods to locate and transform the relevant characteristics of the input for the goal of classification. In particular, we focus on an experimental analysis of explanations produced by several XAI methods on an ML system trained on a typical EEG dataset for emotion recognition. Results show that many relevant components found by XAI methods are shared across the sessions and can be used to build a system able to generalise better. However, relevant components of the input signal also appear to be highly dependent on the input itself
SHAP-based explanations to improve classification systems
Full text linkExplainable Artificial Intelligence (XAI) is a field usually dedicated to offering insights into the decision-making mechanisms of AI models. Its purpose is to enable users to comprehend the reasoning behind the results provided by these models, going beyond mere outputs. In addition, one of the main goals of XAI is to improve the performance of AI models by exploiting the explanations of their decision-making processes. However, a predominant portion of XAI research concentrates on elucidating the functioning of AI systems, with comparatively fewer studies delving into how XAI techniques can be leveraged to enhance the performance of an AI system. This underlines a potential area for further exploration and development in the field of XAI. In this paper we focus on the possibility to enhance the performance of an already trained AI model. To this aim we propose a new scheme of interaction between explanations provided by SHAP XAI method and computations of the responses of a given AI model. This new proposal was tested using the well-known CIFAR-10 dataset and EfficientNet-B2 model, showing promising results
- …
