Case-Based Reasoning relies on the underlying hypothesis that similar problems have similar solutions. The extent to which this hypothesis holds good in the case base has been used by CBR designers as a measure of case base complexity, which in turn gives insights on the generalization ability of the reasoner. Several local and global complexity measures have been proposed in the literature. However, the existing measures rely only on the similarity knowledge to compute complexity. We propose a new complexity measure called Reachability-Based Complexity Measure (RBCM) that goes beyond the similarity knowledge to include the effects of all knowledge containers in the reasoner. The proposed measure is evaluated on several real-world datasets and results suggest that RBCM corroborates well with the generalization accuracy of the reasoner.
Deep convolutional sum-product networks (DCSPNs) have very recently been introduced and shown to yield state-of-the-art results in image completion tasks. A DCSPN consists of a tree structure (a directed acyclic graph) coupled with parameters of the structure. Given that DCSPNs are in their infancy, many open questions remain regarding the properties and topology of its tree structure. In this paper, we undertake three investigations pertaining to the DCSPN structure. The first two studies revolve around the original structure put forth in the seminal paper. These studies increase the number of pooling layers and vary the hyperparameters in attempts to improve accuracy. The third inquiry suggests a new DCSPN tree structure that significantly lowers the training time at some modest expense of accuracy.
During opinion formation, interacting agents can be assumed to be engaging in learning and decision-making processes to satisfy their individual goals. These goals are determined by the agents' preferences - which are often unknown, complex and unpredictable. Most opinion formation frameworks however, assume static preferences and fail to model practical situations where human preferences change. We propose a new framework to simulate the process of opinion formation under uncertainty and dynamism. Agents who are unaware of their implicit contextual preferences utilize inverse reinforcement learning to compute reward functions that determines their preferences. Reinforcement learning is subsequently used to optimize the agents' behavior and satisfy their individual goals. The novelty of our approach lies in its ability to capture uncertainty and dynamism in the agent's preferences, which are assumed to be unknown initially. This framework is compared to a baseline method based on reinforcement learning, and results show its ability to perform better under dynamic scenarios.
Cardellino, Cristian (National University of Córdoba) | Alemany, Laura Alonso (National University of Córdoba) | Teruel, Milagro (National University of Córdoba) | Villata, Serena (Université Côte d'Azur) | Marro, Santiago (National University of Córdoba)
In this paper we adapt the semi-supervised deep learning architecture known as Convolutional Ladder Networks, from the domain of computer vision, and explore how well it works for a semi-supervised Named Entity Recognition and Classification task with legal data. The idea of exploring a semi-supervised technique is to asses the impact of large amounts of unsupervised data (cheap to obtain) in specific tasks that have little annotated data, in order to develop robust models that are less prone to overfitting. In order to achieve this, first we must check the impact on a task that is easier to measure. We are presenting some preliminary results, however, the experiments carried out show some very interesting insights that foster further research in the topic.
Anomaly detection methods abound and are used extensively in streaming settings in a wide variety of domains. But a strength can also be a weakness; given the vast number of methods, how can one select the best method for their application? Unfortunately, there is no one best way for all domains. Existing literature is focused on creating new anomaly detection methods or creating large frameworks for experimenting with multiple methods at the same time. As the literature continues to grow, extensive evaluation of every available anomaly detection method is not feasible. To reduce this evaluation burden, in this paper we present a framework to intelligently choose the optimal anomaly detection methods based on the characteristics the time series displays. We provide a comprehensive experimental validation of multiple anomaly detection methods over different time series characteristics to form guidelines. Applying our framework can save time and effort by surfacing the most promising anomaly detection methods instead of experimenting extensively with a rapidly expanding library of anomaly detection methods.
This paper presents the first results of the research into AI-based support of the room configuration process during the early design phases in architecture. Room configuration (also: room layout or space layout) is an essential stage of the initial design phase: its results are crucial for user-friendliness and success of the planned utilization of the architectural object. Our approach takes into account different possible actions of the configuration process, such as adding, removing, or (re)assigning of the room type. Its mode of operation is based on specific process chain clusters, where each cluster represents a contextual subset of previous configuration steps and provides a recurrent neural network trained on this cluster data only to suggest the next step, and a case base that is used to determine if the current process chain belongs to this cluster. The most similar cluster then tries to suggest the next step of the process. The approach is implemented in a distributed CBR framework for support of early conceptual design in architecture and was evaluated with a high number of process chain queries to prove its general suitability.
Discovering causal relations in a knowledge base represents nowadays a challenging issue, as it gives a brand new way of understanding complex domains. In this paper, we present a method to combine an ontology with an object-oriented extension of the Bayesian networks (BNs), called probabilistic relational model (PRM), in order to help a user to check his/her assumption on causal relations between data and to discover new relationships. This assumption is also important as it guides the PRM construction and provide a learning under causal constraints.
Classification problem in authorship attribution consists of choosing the correct author of a document from an exhaustive list of candidates presented by the samples of their writing. A typical approach is to assign a vector representing measurements of a stylometric feature to each sample document and apply a supervised machine learning method to build a classifier. Different classifiers vary in the accuracy and attributions of the disputed documents. In our previous research, we have shown that a large number of classifiers can be combined into an effective jury via weighted voting. Such a jury is almost always more accurate than individual classifiers.
The lifted dynamic junction tree algorithm (LDJT) efficiently answers filtering and prediction queries for probabilistic relational temporal models by building and then reusing a first-order cluster representation of a knowledge base for multiple queries and time steps. Specifically, this paper contributes (i) a relational forward backward algorithm with LDJT, (ii) smoothing for hindsight queries, and (iii) different approaches to instantiate a first-order cluster representation during a backward pass. Further, our relational forward backward algorithm makes hindsight queries with huge lags feasible. LDJT answers multiple temporal queries faster than the static lifted junction tree algorithm on an unrolled model, which performs smoothing during message passing.
Classic k-Nearest Neighbor (kNN) algorithms approximate a regression or classification function at a query point based on the k-nearest training observations. In real-world datasets, however, the set of k neighbors is frequently not uniformly distributed around a given query point. This can result in a locally biased estimate and thus in degraded regression or classification results. This paper presents two new kNN algorithms that adjust the weight of the k-nearest neighbors to achieve a more balanced distribution. Experiments on real-world datasets and a range of synthetic training distributions and noise levels identify conditions under which the algorithms can improve accuracy with minimal increase in computation time.