In recent years, neural systems have demonstrated highly effective learning ability and superior perception intelligence. However, they have been found to lack effective reasoning and cognitive ability. On the other hand, symbolic systems exhibit exceptional cognitive intelligence but suffer from poor learning capabilities when compared to neural systems. Recognizing the advantages and disadvantages of both methodologies, an ideal solution emerges: combining neural systems and symbolic systems to create neural-symbolic learning systems that possess powerful perception and cognition. The purpose of this paper is to survey the advancements in neural-symbolic learning systems from four distinct perspectives: challenges, methods, applications, and future directions. By doing so, this research aims to propel this emerging field forward, offering researchers a comprehensive and holistic overview. This overview will not only highlight the current state-of-the-art but also identify promising avenues for future research.

We describe parametrised motion planning algorithms for systems controlling objects represented by points that move without collisions in an even dimensional Euclidean space and in the presence of up to three obstacles with \emph{a priori} unknown positions. Our algorithms are optimal in the sense that the parametrised local planners have minimal posible size.

Passenger clustering based on travel records is essential for transportation operators. However, existing methods cannot easily cluster the passengers due to the hierarchical structure of the passenger trip information, namely: each passenger has multiple trips, and each trip contains multi-dimensional multi-mode information. Furthermore, existing approaches rely on an accurate specification of the clustering number to start, which is difficult when millions of commuters are using the transport systems on a daily basis. In this paper, we propose a novel Tensor Dirichlet Process Multinomial Mixture model (Tensor-DPMM), which is designed to preserve the multi-mode and hierarchical structure of the multi-dimensional trip information via tensor, and cluster them in a unified one-step manner. The model also has the ability to determine the number of clusters automatically by using the Dirichlet Process to decide the probabilities for a passenger to be either assigned in an existing cluster or to create a new cluster: This allows our model to grow the clusters as needed in a dynamic manner. Finally, existing methods do not consider spatial semantic graphs such as geographical proximity and functional similarity between the locations, which may cause inaccurate clustering. To this end, we further propose a variant of our model, namely the Tensor-DPMM with Graph. For the algorithm, we propose a tensor Collapsed Gibbs Sampling method, with an innovative step of "disband and relocating", which disbands clusters with too small amount of members and relocates them to the remaining clustering. This avoids uncontrollable growing amounts of clusters. A case study based on Hong Kong metro passenger data is conducted to demonstrate the automatic process of learning the number of clusters, and the learned clusters are better in within-cluster compactness and cross-cluster separateness.

Enhanced Dengue Outbreak Prediction in Tamilnadu using Meteorological and Entomological data Dr. Varalakshmi M, VIT Vellore, India, Dr. Daphne Lopez, VIT Vellore, India Sponsored by: ISRO Acknowledgement: Dr. VinothKumar S, DD/CHO, Madurai Corporation, TamilNadu Public Health Department, India Abstract This paper focuses on studying the impact of climate data and vector larval indices on dengue outbreak. After a comparative study of the various LSTM models, Bidirectional Stacked LSTM network is selected to analyze the time series climate data and health data collected for the state of Tamil Nadu (India), for the period 2014 to 2020. Prediction accuracy of the model is significantly improved by including the mosquito larval index, an indication of VBD control measure. Introduction Dengue Fever (DF), an outbreak prone viral infection is transmitted by Aedes mosquitoes, which is mostly found in tropical and sub-tropical climatic regions. The infection can result in Dengue Haemorrhagic Fever (DHF), also known as severe dengue which can be fatal.

Anti-vaccine sentiments have been well-known and reported throughout the history of viral outbreaks and vaccination programmes. The COVID-19 pandemic had fear and uncertainty about vaccines which has been well expressed on social media platforms such as Twitter. We analyse Twitter sentiments from the beginning of the COVID-19 pandemic and study the public behaviour during the planning, development and deployment of vaccines expressed in tweets worldwide using a sentiment analysis framework via deep learning models. In this way, we provide visualisation and analysis of anti-vaccine sentiments over the course of the COVID-19 pandemic. Our results show a link between the number of tweets, the number of cases, and the change in sentiment polarity scores during major waves of COVID-19 cases. We also found that the first half of the pandemic had drastic changes in the sentiment polarity scores that later stabilised which implies that the vaccine rollout had an impact on the nature of discussions on social media.

Retrieval-augmented language models (LMs) have received much attention recently. However, typically the retriever is not trained jointly as a native component of the LM, but added to an already-pretrained LM, which limits the ability of the LM and the retriever to adapt to one another. In this work, we propose the Retrieval-Pretrained Transformer (RPT), an architecture and training procedure for jointly training a retrieval-augmented LM from scratch for the task of modeling long texts. Given a recently generated text chunk in a long document, the LM computes query representations, which are then used to retrieve earlier chunks in the document, located potentially tens of thousands of tokens before. Information from retrieved chunks is fused into the LM representations to predict the next target chunk. We train the retriever component with a semantic objective, where the goal is to retrieve chunks that increase the probability of the next chunk, according to a reference LM. We evaluate RPT on four long-range language modeling tasks, spanning books, code, and mathematical writing, and demonstrate that RPT improves retrieval quality and subsequently perplexity across the board compared to strong baselines.

In astrophysics, a gravitational lens is a matter distribution (e.g., a black hole) able to bend the trajectory of transiting light, similar to an optical lens. Such apparent distortion is caused by the curvature of the geometry of space-time around the massive body acting as a lens, a phenomenon that forces the light to travel along the geodesics (i.e., the shortest paths in the curved space-time). Strong and weak gravitational lensing focus on the effects produced by particularly massive bodies (e.g., galaxies and black holes), while microlensing addresses the consequences produced by lighter entities (e.g., stars). This research proposes an approach to automatically classify strong gravitational lenses with respect to the lensed objects and to their evolution through time. Automatically finding and classifying gravitational lenses is a major challenge in astrophysics. As [103, 91, 39, 44] show, gravitational lensing systems can be complex, ubiquitous and hard to detect without computer-aided data processing. The volumes of data gathered by contemporary instruments make manual inspection unfeasible. As an example, the Vera C. Rubin Observatory is expected to collect petabytes of data [108]. Moreover, strong lensing is involved in major astrophysical problems: studying massive bodies that are too faint to be analyzed with current instrumentation; characterizing the geometry, content and kinematics of the universe; and investigating mass distribution in the galaxy formation process [103].

This work introduces an attention mechanism for image classifiers and the corresponding deep neural network (DNN) architecture, dubbed ISNet. During training, the ISNet uses segmentation targets to learn how to find the image's region of interest and concentrate its attention on it. The proposal is based on a novel concept, background relevance minimization in LRP explanation heatmaps. It can be applied to virtually any classification neural network architecture, without any extra computational cost at run-time. Capable of ignoring the background, the resulting single DNN can substitute the common pipeline of a segmenter followed by a classifier, being faster and lighter. After injecting synthetic bias in images' backgrounds (in diverse applications), we compare the ISNet to multiple state-of-the-art neural networks, and quantitatively demonstrate its superior capacity of minimizing the bias influence over the classifier decisions. The tasks of COVID-19 and tuberculosis detection in chest X-rays commonly employ mixed training databases, which naturally foster background bias and shortcut learning. By focusing on lungs, the ISNet reduced shortcut learning, leading to significantly superior generalization to external (out-of-distribution) test datasets. ISNet presents an accurate, fast, and light methodology to ignore backgrounds and improve generalization.

In contrast, one of the specific language-learning chatbots is LangAI, launched in March by Federico Ruiz Cassarino. Mr Ruiz Cassarino drew on his own experiences of learning English after moving from Uruguay to the UK. His English skills improved dramatically from speaking every day, compared to more academic methods. He's now using his own app to work on his Italian.

We present $\nu$-Flows, a novel method for restricting the likelihood space of neutrino kinematics in high energy collider experiments using conditional normalizing flows and deep invertible neural networks. This method allows the recovery of the full neutrino momentum which is usually left as a free parameter and permits one to sample neutrino values under a learned conditional likelihood given event observations. We demonstrate the success of $\nu$-Flows in a case study by applying it to simulated semileptonic $t\bar{t}$ events and show that it can lead to more accurate momentum reconstruction, particularly of the longitudinal coordinate. We also show that this has direct benefits in a downstream task of jet association, leading to an improvement of up to a factor of 1.41 compared to conventional methods.