Scientific paper retrieval is essential for supporting literature discovery and research. While dense retrieval methods demonstrate effectiveness in general-purpose tasks, they often fail to capture fine-grained scientific concepts that are essential for accurate understanding of scientific queries. Recent studies also use large language models (LLMs) for query understanding; however, these methods often lack grounding in corpus-specific knowledge and may generate unreliable or unfaithful content. To overcome these limitations, we propose SemRank, an effective and efficient paper retrieval framework that combines LLM-guided query understanding with a concept-based semantic index. Each paper is indexed using multi-granular scientific concepts, including general research topics and detailed key phrases. At query time, an LLM identifies core concepts derived from the corpus to explicitly capture the query's information need. These identified concepts enable precise semantic matching, significantly enhancing retrieval accuracy. Experiments show that SemRank consistently improves the performance of various base retrievers, surpasses strong existing LLM-based baselines, and remains highly efficient.

The multimodal deep neural networks, represented by CLIP, have generated rich downstream applications owing to their excellent performance, thus making understanding the decision-making process of CLIP an essential research topic. Due to the complex structure and the massive pre-training data, it is often regarded as a black-box model that is too difficult to understand and interpret. Concept-based models map the black-box visual representations extracted by deep neural networks onto a set of human-understandable concepts and use the concepts to make predictions, enhancing the transparency of the decision-making process. However, these methods involve the datasets labeled with fine-grained attributes by expert knowledge, which incur high costs and introduce excessive human prior knowledge and bias. In this paper, we observe the long-tail distribution of concepts, based on which we propose a two-stage Concept Selection Model (CSM) to mine core concepts without introducing any human priors. The concept greedy rough selection algorithm is applied to extract head concepts, and then the concept mask fine selection method performs the extraction of core concepts. Experiments show that our approach achieves comparable performance to end-to-end black-box models, and human evaluation demonstrates that the concepts discovered by our method are interpretable and comprehensible for humans.

Although neural models have achieved remarkable performance, they still encounter doubts due to the intransparency. To this end, model prediction explanation is attracting more and more attentions. However, current methods rarely incorporate external knowledge and still suffer from three limitations: (1) Neglecting concept completeness. Merely selecting concepts may not sufficient for prediction. (2) Lacking concept fusion. Failure to merge semantically-equivalent concepts. (3) Difficult in manipulating model behavior. Lack of verification for explanation on original model. To address these issues, we propose a novel knowledge-aware neuron interpretation framework to explain model predictions for image scene classification. Specifically, for concept completeness, we present core concepts of a scene based on knowledge graph, ConceptNet, to gauge the completeness of concepts. Our method, incorporating complete concepts, effectively provides better prediction explanations compared to baselines. Furthermore, for concept fusion, we introduce a knowledge graph-based method known as Concept Filtering, which produces over 23% point gain on neuron behaviors for neuron interpretation. At last, we propose Model Manipulation, which aims to study whether the core concepts based on ConceptNet could be employed to manipulate model behavior. The results show that core concepts can effectively improve the performance of original model by over 26%.

Nash equilibrium[1] of normal-form game was proposed decades ago, yet even whether PTAS exists for it remains undecided, not to mention for equilibriums of games with dynamics. PTAS for equilibriums of games is important itself in game theory, and the confirmation of its existence may impact multi-agent reinforcement learning research. First, the existence of PTAS relates to the practicality of the amount of computational power in achieving equilibriums of large scale games. It has been proved that exactly computing a Nash equilibrium of a static game is in PPAD-hard class of complexity[2]. Ignoring the possibility that PPAD itself is of polynomial-time[3], PTAS describes methods that approximately compute Nash equilibriums efficiently. Second, the confirmation of previously unknown existence of PTAS for games implies possibility to fundamentally solve the problems of non-stationarity in training and curse of dimensionality[4] in multi-agent reinforcement learning at the same time. Both the two problems are related to the absence of PTAS for equilibriums of games. Non-stationarity in training relates to the fact that existing polynomial-time methods lack convergence guarantee to equilibriums, and curse of dimensionality relates to the fact that methods with convergence guarantee lack polynomial-time complexity.

The purpose of this book is to teach you modern linear algebra. But this is not about memorizing some key equations and slugging through abstract proofs; the purpose is to teach you how to think about matrices, vectors, and operations acting upon them. You will develop a geometric intuition for why linear algebra is the way it is. And you will understand how to implement linear algebra concepts in Python code, with a focus on applications in machine learning and data science. Many traditional linear algebra textbooks avoid numerical examples in the interest of generalizations, expect you to derive difficult proofs on your own, and teach myriad concepts that have little or no relevance to application or implementation in computers.

Python - The Practical Guide [2023 Edition] - Learn Python from the ground up and use Python to build a hands-on project from scratch!

Editor's note: In the interest of full transparency, Machine Learning Mastery is KDnuggets' sister site. The author was presented a copy of the book in question and granted full autonomy over their review. Most of the people I know can build, validate, and deploy machine learning models, but they don't know the basics of Python language. Their primary focus is on model architects instead of learning production-ready coding practices. These software engineering practices are necessary that will make you productive.

Artificial intelligence and deep learning. The last 10 years have seen huge advancements in machine learning, a part of artificial intelligence where …

Based on rectangle theory of formal concept and set covering theory, the concept reduction preserving binary relations is investigated in this paper. It is known that there are three types of formal concepts: core concepts, relative necessary concepts and unnecessary concepts. First, we present the new judgment results for relative necessary concepts and unnecessary concepts. Second, we derive the bounds for both the maximum number of relative necessary concepts and the maximum number of unnecessary concepts and it is a difficult problem as either in concept reduction preserving binary relations or attribute reduction of decision formal contexts, the computation of formal contexts from formal concepts is a challenging problem. Third, based on rectangle theory of formal concept, a fast algorithm for reducing attributes while preserving the extensions for a set of formal concepts is proposed using the extension bit-array technique, which allows multiple context cells to be processed by a single 32-bit or 64-bit operator. Technically, the new algorithm could store both formal context and extent of a concept as bit-arrays, and we can use bit-operations to process set operations "or" as well as "and". One more merit is that the new algorithm does not need to consider other concepts in the concept lattice, thus the algorithm is explicit to understand and fast. Experiments demonstrate that the new algorithm is effective in the computation of attribute reductions.

Can I get a certificate after completing the course? Are there any other coupons available for this course? Note: 100% OFF Udemy coupon codes are valid for maximum 3 days only. Look for "ENROLL NOW" button at the end of the post. Disclosure: This post may contain affiliate links and we may get small commission if you make a purchase.