The ability to distinguish between different movie scenes is critical for understanding the storyline of a movie. However, accurately detecting movie scenes is often challenging as it requires the ability to reason over very long movie segments. This is in contrast to most existing video recognition models, which are typically designed for short-range video analysis. This work proposes a State-Space Transformer model that can efficiently capture dependencies in long movie videos for accurate movie scene detection. Our model, dubbed TranS4mer, is built using a novel S4A building block, which combines the strengths of structured state-space sequence (S4) and self-attention (A) layers. Given a sequence of frames divided into movie shots (uninterrupted periods where the camera position does not change), the S4A block first applies self-attention to capture short-range intra-shot dependencies. Afterward, the state-space operation in the S4A block is used to aggregate long-range inter-shot cues. The final TranS4mer model, which can be trained end-to-end, is obtained by stacking the S4A blocks one after the other multiple times. Our proposed TranS4mer outperforms all prior methods in three movie scene detection datasets, including MovieNet, BBC, and OVSD, while also being $2\times$ faster and requiring $3\times$ less GPU memory than standard Transformer models. We will release our code and models.

本报告描述了我们的提交称为“ tarheels”的EGO4D：对象状态变更分类挑战。我们使用基于变压器的视频识别模型，并利用分隔的时空注意机制来对以中心视频的对象状态变化进行分类。我们的提交在挑战中取得了第二好的表现。此外，我们进行了一项消融研究，以表明识别以egipentric视频中的对象状态变化需要时间建模能力。最后，我们提出了几个积极和负面的例子，以可视化模型的预测。该代码可公开可用：https：//github.com/md-mohaiminul/ObjectStateChange

大多数现代视频识别模型旨在在短视频剪辑上运行（例如，长度为5-10）。因此，将此类模型应用于长时间的电影理解任务是一项挑战，通常需要复杂的长期时间推理。最近引入的视频变形金刚通过使用远程时间自我注意来部分解决此问题。但是，由于自我注意力的二次成本，这种模型通常是昂贵且不切实际的。取而代之的是，我们提出了Vis4mer，这是一种有效的远程视频模型，结合了自我注意力的优势和最近引入的结构化状态空间序列（S4）层。我们的模型使用标准的变压器编码器进行短距离时空特征提取，以及多尺度的时间S4解码器，用于随后的远程时间推理。通过逐步减少每个解码器层处的时空特征分辨率和通道维度，Vis4mer在视频中学习了复杂的长期时空依赖性。此外，比相应的基于纯的自我注意力的模型，Vis4mer的价格更快为$ 2.63 \ times $ $，$ 8 \ times $ $ GPU内存。此外，Vis4mer实现最先进的结果，在长期视频理解（LVU）基准中，$ 9 $ 9 $长的电影视频分类任务中的$ 6 $。此外，我们表明我们的方法成功地将其推广到其他领域，从而在早餐和硬币程序活动数据集中取得了竞争成果。该代码可在以下网址公开获取：https：//github.com/md-mohaiminul/vis4mer。

Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real-world applications of RL, recovering underlying latent states is crucial, particularly when sensory inputs contain irrelevant and exogenous information. In this work, we study how information bottlenecks can be used to construct latent states efficiently in the presence of task-irrelevant information. We propose architectures that utilize variational and discrete information bottlenecks, coined as RepDIB, to learn structured factorized representations. Exploiting the expressiveness bought by factorized representations, we introduce a simple, yet effective, bottleneck that can be integrated with any existing self-supervised objective for RL. We demonstrate this across several online and offline RL benchmarks, along with a real robot arm task, where we find that compressed representations with RepDIB can lead to strong performance improvements, as the learned bottlenecks help predict only the relevant state while ignoring irrelevant information.

Artificial intelligence(AI) systems based on deep neural networks (DNNs) and machine learning (ML) algorithms are increasingly used to solve critical problems in bioinformatics, biomedical informatics, and precision medicine. However, complex DNN or ML models that are unavoidably opaque and perceived as black-box methods, may not be able to explain why and how they make certain decisions. Such black-box models are difficult to comprehend not only for targeted users and decision-makers but also for AI developers. Besides, in sensitive areas like healthcare, explainability and accountability are not only desirable properties of AI but also legal requirements -- especially when AI may have significant impacts on human lives. Explainable artificial intelligence (XAI) is an emerging field that aims to mitigate the opaqueness of black-box models and make it possible to interpret how AI systems make their decisions with transparency. An interpretable ML model can explain how it makes predictions and which factors affect the model's outcomes. The majority of state-of-the-art interpretable ML methods have been developed in a domain-agnostic way and originate from computer vision, automated reasoning, or even statistics. Many of these methods cannot be directly applied to bioinformatics problems, without prior customization, extension, and domain adoption. In this paper, we discuss the importance of explainability with a focus on bioinformatics. We analyse and comprehensively overview of model-specific and model-agnostic interpretable ML methods and tools. Via several case studies covering bioimaging, cancer genomics, and biomedical text mining, we show how bioinformatics research could benefit from XAI methods and how they could help improve decision fairness.

Task agnostic generative pretraining (GPT) has recently proved promising for zero- and few-shot learning, gradually diverting attention from the expensive supervised learning paradigm. Although the community is accumulating knowledge as to capabilities of English-language autoregressive models such as GPT-3 adopting this generative approach, scholarship about these models remains acutely Anglocentric. Consequently, the community currently has serious gaps in its understanding of this class of models, their potential, and their societal impacts in diverse settings, linguistic traditions, and cultures. To alleviate this issue for Arabic, a collection of diverse languages and language varieties with more than $400$ million population, we introduce JASMINE, a suite of powerful Arabic autoregressive Transformer language models ranging in size between 300 million-13 billion parameters. We pretrain our new models with large amounts of diverse data (400GB of text) from different Arabic varieties and domains. We evaluate JASMINE extensively in both intrinsic and extrinsic settings, using a comprehensive benchmark for zero- and few-shot learning across a wide range of NLP tasks. We also carefully develop and release a novel benchmark for both automated and human evaluation of Arabic autoregressive models focused at investigating potential social biases, harms, and toxicity in these models. We aim to responsibly release our models with interested researchers, along with code for experimenting with them

Climate change has increased the intensity, frequency, and duration of extreme weather events and natural disasters across the world. While the increased data on natural disasters improves the scope of machine learning (ML) in this field, progress is relatively slow. One bottleneck is the lack of benchmark datasets that would allow ML researchers to quantify their progress against a standard metric. The objective of this short paper is to explore the state of benchmark datasets for ML tasks related to natural disasters, categorizing them according to the disaster management cycle. We compile a list of existing benchmark datasets introduced in the past five years. We propose a web platform - NADBenchmarks - where researchers can search for benchmark datasets for natural disasters, and we develop a preliminary version of such a platform using our compiled list. This paper is intended to aid researchers in finding benchmark datasets to train their ML models on, and provide general directions for topics where they can contribute new benchmark datasets.

The neural implementation of operant conditioning with few trials is unclear. We propose a Hippocampus-Inspired Cognitive Architecture (HICA) as a neural mechanism for operant conditioning. HICA explains a learning mechanism in which agents can learn a new behavior policy in a few trials, as mammals do in operant conditioning experiments. HICA is composed of two different types of modules. One is a universal learning module type that represents a cortical column in the neocortex gray matter. The working principle is modeled as Modulated Heterarchical Prediction Memory (mHPM). In mHPM, each module learns to predict a succeeding input vector given the sequence of the input vectors from lower layers and the context vectors from higher layers. The prediction is fed into the lower layers as a context signal (top-down feedback signaling), and into the higher layers as an input signal (bottom-up feedforward signaling). Rewards modulate the learning rate in those modules to memorize meaningful sequences effectively. In mHPM, each module updates in a local and distributed way compared to conventional end-to-end learning with backpropagation of the single objective loss. This local structure enables the heterarchical network of modules. The second type is an innate, special-purpose module representing various organs of the brain's subcortical system. Modules modeling organs such as the amygdala, hippocampus, and reward center are pre-programmed to enable instinctive behaviors. The hippocampus plays the role of the simulator. It is an autoregressive prediction model of the top-most level signal with a loop structure of memory, while cortical columns are lower layers that provide detailed information to the simulation. The simulation becomes the basis for learning with few trials and the deliberate planning required for operant conditioning.

Network intrusion detection systems (NIDSs) play an important role in computer network security. There are several detection mechanisms where anomaly-based automated detection outperforms others significantly. Amid the sophistication and growing number of attacks, dealing with large amounts of data is a recognized issue in the development of anomaly-based NIDS. However, do current models meet the needs of today's networks in terms of required accuracy and dependability? In this research, we propose a new hybrid model that combines machine learning and deep learning to increase detection rates while securing dependability. Our proposed method ensures efficient pre-processing by combining SMOTE for data balancing and XGBoost for feature selection. We compared our developed method to various machine learning and deep learning algorithms to find a more efficient algorithm to implement in the pipeline. Furthermore, we chose the most effective model for network intrusion based on a set of benchmarked performance analysis criteria. Our method produces excellent results when tested on two datasets, KDDCUP'99 and CIC-MalMem-2022, with an accuracy of 99.99% and 100% for KDDCUP'99 and CIC-MalMem-2022, respectively, and no overfitting or Type-1 and Type-2 issues.

Accurate recognition of food items along with quality assessment is of paramount importance in the agricultural industry. Such automated systems can speed up the wheel of the food processing sector and save tons of manual labor. In this connection, the recent advancement of Deep learning-based architectures has introduced a wide variety of solutions offering remarkable performance in several classification tasks. In this work, we have exploited the concept of Densely Connected Convolutional Neural Networks (DenseNets) for fruit quality assessment. The feature propagation towards the deeper layers has enabled the network to tackle the vanishing gradient problems and ensured the reuse of features to learn meaningful insights. Evaluating on a dataset of 19,526 images containing six fruits having three quality grades for each, the proposed pipeline achieved a remarkable accuracy of 99.67%. The robustness of the model was further tested for fruit classification and quality assessment tasks where the model produced a similar performance, which makes it suitable for real-life applications.