Plausible counterfactual explanations (p-CFEs) are perturbations that minimally modify inputs to change classifier decisions while remaining plausible under the data distribution. In this study, we demonstrate that classifiers can be trained on p-CFEs labeled with induced \emph{incorrect} target classes to classify unperturbed inputs with the original labels. While previous studies have shown that such learning is possible with adversarial perturbations, we extend this paradigm to p-CFEs. Interestingly, our experiments reveal that learning from p-CFEs is even more effective: the resulting classifiers achieve not only high in-distribution accuracy but also exhibit significantly reduced bias with respect to spurious correlations.

Transient noise (glitches) in LIGO data hinders the detection of gravitational waves (GW). The Gravity Spy project has categorized these noise events into various classes. With the O3 run, there is the inclusion of two additional noise classes and thus a need to train new models for effective classification. We aim to classify glitches in LIGO data into 22 existing classes from the first run plus 2 additional noise classes from O3a using the Vision Transformer (ViT) model. We train a pre-trained Vision Transformer (ViT-B/32) model on a combined dataset consisting of the Gravity Spy dataset with the additional two classes from the LIGO O3a run. We achieve a classification efficiency of 92.26%, demonstrating the potential of Vision Transformer to improve the accuracy of gravitational wave detection by effectively distinguishing transient noise. Key words: gravitational waves --vision transformer --machine learning

In political discourse and geopolitical analysis, national leaders words hold profound significance, often serving as harbingers of pivotal historical moments. From impassioned rallying cries to calls for caution, presidential speeches preceding major conflicts encapsulate the multifaceted dynamics of decision-making at the apex of governance. This project aims to use deep learning techniques to decode the subtle nuances and underlying patterns of US presidential rhetoric that may signal US involvement in major wars. While accurate classification is desirable, we seek to take a step further and identify discriminative features between the two classes (i.e. interpretable learning). Through an interdisciplinary fusion of machine learning and historical inquiry, we aspire to unearth insights into the predictive capacity of neural networks in discerning the preparatory rhetoric of US presidents preceding war. Indeed, as the venerable Prussian General and military theorist Carl von Clausewitz admonishes, War is not merely an act of policy but a true political instrument, a continuation of political intercourse carried on with other means (Clausewitz, 1832).

Treatment plans often involve multiple neurodevelopmental condition marked by difficulties in social sessions with different therapists, and the absence of a standardized interaction, communication impediments, and repetitive behaviors. This fragmented approach continue to pose significant challenges due to the variability in can impede effective communication and coordination among symptomatology and the necessity for multidisciplinary care healthcare providers, adversely affecting the quality of care. This paper investigates the potential of Artificial Furthermore, parents and caregivers may find it challenging to access Intelligence (AI) to augment the capabilities of healthcare and manage the extensive records necessary for consistent treatment, professionals and caregivers in managing ASD. We have developed further complicating the overall management of ASD. a sophisticated algorithm designed to analyze facial and bodily Artificial Intelligence (AI) presents a promising solution to the expressions during daily activities of both autistic and non-autistic complexities involved in diagnosing and treating Autism Spectrum children, leading to the development of a powerful deep learningbased Disorder (ASD) [6]. AI-powered tools have the potential to autism detection system. Our study demonstrated that AI standardize the diagnostic process by analyzing extensive datasets to models, specifically the Xception and ResNet50V2 architectures, uncover patterns and correlations that might be overlooked by human achieved high accuracy in diagnosing Autism Spectrum Disorder evaluators.

Brain tumor segmentation is a critical task in medical image analysis, aiding in the diagnosis and treatment planning of brain tumor patients. The importance of automated and accurate brain tumor segmentation cannot be overstated. It enables medical professionals to precisely delineate tumor regions, assess tumor growth or regression, and plan targeted treatments. Various deep learning-based techniques proposed in the literature have made significant progress in this field, however, they still face limitations in terms of accuracy due to the complex and variable nature of brain tumor morphology. In this research paper, we propose a novel Hybrid Multihead Attentive U-Net architecture, to address the challenges in accurate brain tumor segmentation, and to capture complex spatial relationships and subtle tumor boundaries. The U-Net architecture has proven effective in capturing contextual information and feature representations, while attention mechanisms enhance the model's ability to focus on informative regions and refine the segmentation boundaries. By integrating these two components, our proposed architecture improves accuracy in brain tumor segmentation. We test our proposed model on the BraTS 2020 benchmark dataset and compare its performance with the state-of-the-art well-known SegNet, FCN-8s, and Dense121 U-Net architectures. The results show that our proposed model outperforms the others in terms of the evaluated performance metrics.

Locomotion mechanics of legged robots are suitable when pacing through difficult terrains. Recognising terrains for such robots are important to fully yoke the versatility of their movements. Consequently, robotic terrain classification becomes significant to classify terrains in real time with high accuracy. The conventional classifiers suffer from overfitting problem, low accuracy problem, high variance problem, and not suitable for live dataset. On the other hand, classifying a growing dataset is difficult for convolution based terrain classification. Supervised recurrent models are also not practical for this classification. Further, the existing recurrent architectures are still evolving to improve accuracy of terrain classification based on live variable-length sensory data collected from legged robots. This paper proposes a new semi-supervised method for terrain classification of legged robots, avoiding preprocessing of long variable-length dataset. The proposed method has a stacked Long Short-Term Memory architecture, including a new loss regularization. The proposed method solves the existing problems and improves accuracy. Comparison with the existing architectures show the improvements.

The neurons in the brain produces electric signals and a collective firing of these electric signals gives rise to brainwaves. These brainwave signals are captured using EEG (Electroencephalogram) devices as micro voltages. These sequence of signals captured by EEG sensors have embedded features in them that can be used for classification. The signals can be used as an alternative input for people suffering from severe locomotive disorder.Classification of different colors can be mapped for many functions like directional movement. In this paper, raw EEG signals from NeuroSky Mindwave headset (a single electrode EEG sensor) have been classified with an attention based Deep Learning Network. Attention based LSTM Networks have been implemented for classification of two different colors and four different colors. An accuracy of 93.5\% was obtained for classification of two colors and an accuracy of 65.75\% was obtained for classifcation of four signals using the mentioned attention based LSTM network.

Pooling operations have been a mainstay in convolutional neural networks for some time. While processes like max pooling and average pooling have often taken more of the center stage, their less known cousins global max pooling and global average pooling have become equally as important. In this article, we will be exploring what the global variants of the two common pooling techniques entail and how they compare to one another. Many beginners in computer vision often get introduced to convolutional neural networks as the ideal neural network for image data as it retains the spatial structure of the input image while learning/extracting features from them. By doing so it is able to learn relationships between neighboring pixels and the position of objects in the image thereby making it a very powerful neural network.

Fractures are widely developed in hydrocarbon reservoirs and constitute the accumulation spaces and transport channels of oil and gas. Fracture detection is a fundamental task for reservoir characterization. From prestack seismic gathers, anisotropic analysis and inversion were commonly applied to characterize the dominant orientations and relative intensities of fractures. However, the existing methods were mostly based on the vertical aligned facture hypothesis, it is impossible for them to recognize fracture dip. Furthermore, it is difficult or impractical for existing methods to attain the real fracture densities. Based on data-driven deep learning, this paper designed a convolutional neural network to perform prestack fracture detection. Capitalizing on the connections between seismic responses and fracture parameters, a suitable azimuth dataset was firstly generated through fracture effective medium modeling and anisotropic plane wave analyzing. Then a multi-input and multi-output convolutional neural network was constructed to simultaneously detect fracture density, dip and strike azimuth. The application on a practical survey validated the effectiveness of the proposed CNN model.

Steven Thompson Computer Science Liverpool John Moores University Liverpool, Merseyside S.R.Thompson@LJMU.AC.UK Denis Reilly Computer Science Liverpool John Moores University Liverpool, Merseyside D.Reilly@LJMU.AC.UK Paul Fergus Computer Science Liverpool John Moores University Liverpool, Merseysde P.Fergus@LJMU.AC.UK Carl Chalmers Computer Science Liverpool John Moores University Liverpool, Merseyside C.Chalmers@LJMU.AC.UK Abstract --The study in this paper presents a one-dimensional convolutional neural network (1DCNN) model, designed for the automated detection of obstructive Sleep Apnoea (OSA) captured from single-channel electrocardiogram (ECG) signals. The system provides mechanisms in clinical practice that help diagnose patients suffering with OSA. Using the state-of-the-art in 1DCNNs, a model is constructed using convolutional, max pooling layers and a fully connected Multilayer Perceptron (MLP) consisting of a hidden layer and SoftMax output for classification. The 1DCNN extracts prominent features, which are used to train an MLP. The model is trained using segmented ECG signals grouped into 5 unique datasets of set window sizes. A total of 6514 minutes of Apnoea was recorded. Evaluation of the model is performed using a set of standard metrics which show the proposed model achieves high classification results in both training and validation using our windowing strategy, particularly W 500 (Sensitivity 0.9705, Specificity 0.9725, F1_Score 0.9717, Kappa_Score 0.9430, Log_Loss 0.0836, ROCAUC 0.9945). This demonstrates the model can identify the presence of Apnoea with a high degree of accuracy.