Abstract

The current study examines the role of constraints in well-defined problem-solving in ill-defined problem-solving. We chose variants of Raven’s advanced progressive matri- ces(APM) for well-defined problem-solving and creative rea- soning tasks (CRT) for ill-defined problem-solving. Using traditional APM, we created a novel version of APM with comparatively lesser constraints available to solve the puzzle, called creative APM(cAPM). The cAPM task was designed to induce divergent thinking along with convergent thinking. It is assumed that the difference in constraints changes the na- ture of the problem space in solving APM and cAPM and may differently affect the following creative reasoning task. We randomly assigned 50 participants to perform APM or cAPM, followed by the CRT, in a fixed order. We observed a sig- nificant effect of constraints available to solve well-defined problems on ill-defined problem-solving. The current result showed higher CRT scores when CRT preceded cAPM (Me- dian = 79.25) than APM (Median = 53.00). The result sug- gests that the flexibility in constraints to solve a well-defined problem induces more divergent thinking alongside convergent thinking and facilitates creative thinking required in ill-defined problem-solving.

Abstract

The Earth is a system of numerous interconnected spheres, such as the climate. Climate's global and regional influence requires understanding its evolution in space and time to improve knowledge and forecasts. Analyzing and studying decades of climate data is a data mining challenge. Cluster analysis minimizes data volumes and analyzes behavior by cluster. Understanding invariant behavior is as crucial as understanding variable behavior. Gridded data from two sources: Grided IMD data and CMIP5 HadCM3 decadal experiments, are studied using K-Means and MiSTIC clustering techniques to explore spatiotemporal clustering of maximum and minimum temperatures. The boundaries of k-means clustering correspond with topography. The Indian subcontinent's physiographic, climatic, and topographical characteristics affect MiSTIC's core areas. Both techniques yield overlapping clusters. The datasets' MiSTIC cluster counts varied significantly. The impact of data on this technique is shown in how the datasets group the Himalayas.

Abstract

A code of length n is said to be (combinatorially) (ρ, L)-list decodable if the Hamming ball of radius ρn around any vector in the ambient space does not contain more than L codewords. We study a recently introduced class of higher order MDS codes, which are closely related (via duality) to codes that achieve a generalized Singleton bound for list decodability. For some ℓ ≥ 1, higher order MDS codes of length n, dimension k, and order ℓ are denoted as (n, k)-MDS(ℓ) codes. We present a number of results on the structure of these codes, identifying the ‘extend-ability’ of their parameters in various scenarios. Specifically, for some parameter regimes, we identify conditions under which (n1, k1)-MDS(ℓ1) codes can be obtained from (n2, k2)-MDS(ℓ2) codes, via various techniques. We believe that these results will aid in efficient constructions of higher order MDS codes. We also obtain a new field size upper bound for the existence of such codes, which arguably improves over the best known existing bound, in some parameter regimes. Due to space restrictions, the full version of this paper containing proofs of claims is made available in [1].

Abstract

Link forecasting in a temporal Knowledge Graph (tKG) in- volves predicting a future event from a given set of past events. Most previous studies suffered from reduced performance as they disregarded acyclic rules and enforced a tight constraint that all past events must exist in a strict temporal order. This paper proposes a novel explainable rule-based link forecasting framework by introducing two new concepts, namely ‘relaxed temporal cyclic and acyclic random walks’ and ‘link-star rules’. The former concept involves generating rules by performing cyclic and acyclic random walks on a tKG by taking into account the real-world phenomenon that the order of any two events may be ignored if their oc- currence time gap is within a threshold value. Link-star rules are a special class of acyclic rules generated based on the natural phenomenon that history repeats itself after a particular time. Link-star rules eliminate the problem of combinatorial rule explosion, thereby making our frame- work practicable. Experimental results demonstrate that our framework outperforms the state-of-the-art by a substantial margin. The evaluation measures hits@1 and mean reciprocal rank were improved by 45% and 23%, respectively. Keywords: Knowledge Graphs · Graph Analytics · Forecasting

Abstract

Bayesian Optimization (BO) is used to find the global optima of black box functions. In this work, we propose a practical BO method of function compositions where the form of the composition is known but the constituent functions are expensive to evaluate. By assuming an independent Gaussian process (GP) model for each of the constituent black-box function, we propose EI and UCB based BO algorithms and demonstrate their ability to outperform vanilla BO and the current state-of-art algorithms. We demonstrate a novel application of the proposed methods to dynamic pricing in revenue management when the underlying demand function is expensive to evaluate.

Abstract

This paper proposes a scalable distributed video analytics framework that can process thousands of video streams from sources such as CCTV cameras using semantic scene analysis. The main idea is to deploy deep learning pipelines on the fog nodes and generate semantic scene description records (SDRs) of video feeds from the associated CCTV cameras. These SDRs are transmitted to the cloud instead of video frames saving on network bandwidth. Using these SDRs stored on the cloud database, we can answer many complex queries and perform rich video analytics, within extremely low latencies. There is no need to scan and process the video streams again on a per query basis. The software architecture on the fog nodes allows for integrating new deep learning pipelines dynamically into the existing system, thereby supporting novel analytics and queries. We demonstrate the effectiveness of the system by proposing a novel distributed algorithm for real-time vehicle pursuit. The proposed algorithm involves asking multiple spatio-temporal queries in an adaptive fashion to reduce the query processing time and is robust to inaccuracies in the deployed deep learning pipelines and camera failures.

Abstract

The focus of recent research has shifted from merely increasing the Deep Neu- ral Networks (DNNs) performance in various tasks to DNNs which are more interpretable to humans. The field of eXplainable Artificial Intelligence (XAI) has observed various techniques, including saliency-based and concept-based ap- proaches. Concept-based approaches explain the model’s decisions in simple human understandable terms called Concepts. Concepts are human interpretable units of data and the thinking ground of humans. Explanations in terms of concepts enable detecting spurious correlations, inherent biases, or clever-hans. With the ad- vent of concept-based explanations, there have been various concept representation methods and automatic concept discovery algorithms. With automatic concept dis- covery, there are a variety of discovered concept evaluation metrics. Additionally, some approaches use concepts to improve the model explainability and generaliza- tion (Concept Oriented Deep Learning CODL). The concept-based approaches are fairly new, with many new representations coming up while there is very limited work on CODL. We thus provide a systematic review and taxonomy of various concept representations and their discovery algorithms in DNNs, specifically in vision. We also provide details on concept-based model improvement literature being the first to survey CODL methods

Abstract

Humans use abstract concepts instead of hard features for generalization. Recent interpretability research has focused on human-centered concept explanations of neural networks. We present Concept Distillation, a novel method and framework for concept-sensitive training to induce human-centered knowledge into the model. We use Concept Activation Vectors (CAVs) to estimate the model’s sensitivity and possible biases to a given concept. We extend CAVs to ante-hoc training from post-hoc analysis. We distill the conceptual knowledge from a pretrained knowledgeable teacher to a student model focused on a single downstream task. Our method can sensitize or desensitize the student model towards concepts. We show applications of concept-sensitive training to debias classification and to induce prior knowledge into a reconstruction problem. We also introduce the TextureMNIST dataset to evaluate the presence of complex texture biases. We show that concept-sensitive training can improve model interpretability, reduce biases, and induce prior knowledge

Abstract

This paper presents the analysis and results of a data-driven approach for fault detection and isolation in case of complete failure of a single motor on a hexacopter. The proposed approach consists of a two-stage architecture using the Rotation Forest algorithm, which can detect faults without any false alarms and achieve a true positive classification rate of 92.6% and a false positive classification rate of 0.06%. The classification results are compared to other methods such as Logistic Regression, Gaussian Naive Bayes, AdaBoost, and Random Forest. Over 120 datasets containing approximately 21,000 data points are generated in simulation - divided into two sets for training and validation of the model. Outdoor flight tests are performed to validate the classifier algorithm further. We can detect and classify the fault within 60ms of its occurrence. A dataset is published in the open-source domain and can be used for training similar models. The work presented in this paper is data-driven (or model free) since the classifier has no knowledge of the parameters of the UAV and is derived only based on the functional relationship between input and output variables.

Abstract

Music processing is a complex and intriguing phenomenon that has garnered extensive research interest in recent years. In this study, we investigated neural representations of music features by analyzing blood-oxygen-level-dependent (BOLD) signal fMRI activations of selected regions of interest during a continuous listening task. Additionally, we compared these activations to the hidden layer activations of a special class of deep neural networks (DNNs). Using representational similarity analysis, we found a strong correlation between low-level music feature encoding in the human brain regions of the Superior Temporal Gyrus (STG) and Heschl’s gyrus (HG) to the hidden layers of the DNN encoder. Our results suggest that self-supervised DNNs can serve as a reliable architecture to study the music processing domain, which is crucial considering the absence of naturalistic listening conditions in prior research Keywords: neural networks, representation similarity analysis, music cognition, music encoding, neuromusicology