Viral News - CybAI news

20 Aug

Electroencephalogram Emotion Recognition via AUC Maximization

stp2y0 CommentsViral News

arXiv:2408.08979v1 Announce Type: new Abstract: Imbalanced datasets pose significant challenges in areas including neuroscience, cognitive science, and medical diagnostics, where accurately detecting minority classes is essential for robust model performance. This study addresses the issue of class imbalance, using the `Liking' label in the DEAP dataset as an example. Such imbalances are often overlooked by prior research, which typically focuses on the more balanced arousal and valence labels and predominantly uses accuracy metrics to measure model performance. To tackle this issue, we adopt numerical optimization techniques aimed at maximizing the area under the curve (AUC), thus enhancing the detection of…

20 Aug

Image Class Translation Distance: A Novel Interpretable Feature for Image Classification

stp2y0 CommentsViral News

arXiv:2408.08973v1 Announce Type: new Abstract: We propose a novel application of image translation networks for image classification and demonstrate its potential as a more interpretable alternative to conventional black box classification networks. We train a network to translate images between possible classes, and then quantify translation distance, i.e. the degree of alteration needed to conform an image to one class or another. These translation distances can then be examined for clusters and trends, and can be fed directly to a simple classifier (e.g. a support vector machine, SVM), providing comparable accuracy compared to a conventional end-to-end convolutional neural network classifier.…

20 Aug

A Multi-Task and Multi-Label Classification Model for Implicit Discourse Relation Recognition

stp2y0 CommentsViral News

arXiv:2408.08971v1 Announce Type: new Abstract: In this work, we address the inherent ambiguity in Implicit Discourse Relation Recognition (IDRR) by introducing a novel multi-task classification model capable of learning both multi-label and single-label representations of discourse relations. Leveraging the DiscoGeM corpus, we train and evaluate our model on both multi-label and traditional single-label classification tasks. To the best of our knowledge, our work presents the first truly multi-label classifier in IDRR, establishing a benchmark for multi-label classification and achieving SOTA results in single-label classification on DiscoGeM. Additionally, we evaluate our model on the PDTB 3.0 corpus for single-label classification without…

20 Aug

Announcing the Pycharm Integration with Databricks

stp2y0 CommentsViral News

We are excited to announce the latest addition to the Databricks developer experience: the PyCharm Professional Integration with Databricks! This new plugin built by JetBrains, allows you to leverage your favorite IDE features while developing on Databricks, enabling software development best practices and streamlining the path to production.Our partnership with JetBrains highlights our commitment to meet developers where they are - letting customers take advantage of their favorite third party IDE to complement their Databricks developer experience. The PyCharm plugin adds to our growing list of support for IDEs including Databricks for Visual Studio Code and Posit workbench.Check out a…

20 Aug

Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition

stp2y0 CommentsViral News

[Submitted on 16 Aug 2024] View a PDF of the paper titled Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition, by Kenzo Clauw and 2 other authors View PDF HTML (experimental) Abstract:This paper studies emergent phenomena in neural networks by focusing on grokking where models suddenly generalize after delayed memorization. To understand this phase transition, we utilize higher-order mutual information to analyze the collective behavior (synergy) and shared properties (redundancy) between neurons during training. We identify distinct phases before grokking allowing us to anticipate when it occurs. We attribute grokking to an emergent phase transition caused by the…

20 Aug

SHARP-Net: A Refined Pyramid Network for Deficiency Segmentation in Culverts and Sewer Pipes

stp2y0 CommentsViral News

[Submitted on 2 Aug 2024] View a PDF of the paper titled SHARP-Net: A Refined Pyramid Network for Deficiency Segmentation in Culverts and Sewer Pipes, by Rasha Alshawi and 6 other authors View PDF HTML (experimental) Abstract:This paper introduces Semantic Haar-Adaptive Refined Pyramid Network (SHARP-Net), a novel architecture for semantic segmentation. SHARP-Net integrates a bottom-up pathway featuring Inception-like blocks with varying filter sizes (3x3$ and 5x5), parallel max-pooling, and additional spatial detection layers. This design captures multi-scale features and fine structural details. Throughout the network, depth-wise separable convolutions are used to reduce complexity. The top-down pathway of SHARP-Net focuses on…

20 Aug

BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis

stp2y0 CommentsViral News

arXiv:2408.08964v1 Announce Type: new Abstract: The widespread availability of code-mixed data can provide valuable insights into low-resource languages like Bengali, which have limited datasets. Sentiment analysis has been a fundamental text classification task across several languages for code-mixed data. However, there has yet to be a large-scale and diverse sentiment analysis dataset on code-mixed Bengali. We address this limitation by introducing BnSentMix, a sentiment analysis dataset on code-mixed Bengali consisting of 20,000 samples with $4$ sentiment labels from Facebook, YouTube, and e-commerce sites. We ensure diversity in data sources to replicate realistic code-mixed scenarios. Additionally, we propose $14$ baseline methods…

20 Aug

A Classifier-Based Approach to Multi-Class Anomaly Detection Applied to Astronomical Time-Series

stp2y0 CommentsViral News

[Submitted on 5 Aug 2024] View a PDF of the paper titled A Classifier-Based Approach to Multi-Class Anomaly Detection Applied to Astronomical Time-Series, by Rithwik Gupta and 1 other authors View PDF HTML (experimental) Abstract:Automating anomaly detection is an open problem in many scientific fields, particularly in time-domain astronomy, where modern telescopes generate millions of alerts per night. Currently, most anomaly detection algorithms for astronomical time-series rely either on hand-crafted features or on features generated through unsupervised representation learning, coupled with standard anomaly detection algorithms. In this work, we introduce a novel approach that leverages the latent space of a…

20 Aug

PQV-Mobile: A Combined Pruning and Quantization Toolkit to Optimize Vision Transformers for Mobile Applications

stp2y0 CommentsViral News

arXiv:2408.08437v1 Announce Type: new Abstract: While Vision Transformers (ViTs) are extremely effective at computer vision tasks and are replacing convolutional neural networks as the new state-of-the-art, they are complex and memory-intensive models. In order to effectively run these models on resource-constrained mobile/edge systems, there is a need to not only compress these models but also to optimize them and convert them into deployment-friendly formats. To this end, this paper presents a combined pruning and quantization tool, called PQV-Mobile, to optimize vision transformers for mobile applications. The tool is able to support different types of structured pruning based on magnitude importance,…

20 Aug

Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding

stp2y0 CommentsViral News

arXiv:2408.08506v1 Announce Type: new Abstract: Generating long-term texts such as novels using artificial intelligence has always been a challenge. A common approach is to use large language models (LLMs) to construct a hierarchical framework that first plans and then writes. Despite the fact that the generated novels reach a sufficient length, they exhibit poor logical coherence and appeal in their plots and deficiencies in character and event depiction, ultimately compromising the overall narrative quality. In this paper, we propose a method named Extracting Excelsior and Expanding. Ex3 initially extracts structure information from raw novel data. By combining this structure information…