Learning from Observation involves creating agents that observe experts performing tasks and imitate them. Case-Based Reasoning (CBR) is a tool that can be used for this purpose. Regular CBR can only learn memoryless behavior: behavior that doesn't rely on the past. Temporal Backtracking (TB) is an approach to learning state-based behavior that uses recency as its inductive bias, which may or may not be relevant to the agent behavior. We show how TB can be viewed as a particular case of a more generalized case-based approach to learning state-based behavior that can accommodate other inductive biases. We then propose five alternative similarity metrics to learn three different state-based behaviors in a 2D vacuum cleaner domain, and compare their performance to the TB algorithm's performance. We show that none of the proposed metrics (nor TB) is a one-size-fits all algorithm for learning state-based behavior.

We propose a Case-Based Reasoning(CBR) approach for content selection, which is an intermediate step towards generating textual summaries of time series data in the weather prediction domain. Specifically, we handle two significant challenges, the first involving multivariate data that warrants modeling of the interaction of two `channels' (wind speed and direction in our context) and the second involving the effective integration of domain-specific knowledge in the form of rules with data from a case library of past instances of content selection. We present an approach that uses domain knowledge to transform a given raw time series instance into a representation that facilitates effective retrieval of relevant cases, which are then used for change point prediction. We empirically demonstrate that our approach combining CBR and domain rules outperforms classical content selection mechanisms that are based on rules or heuristics alone as well as those that are purely data-driven.

The development of microarray technology has made it possible to assemble biomedical datasets that measure the expression profile of thousands of genes simultaneously. However, such high-dimensional datasets make computation costly and can complicate the interpretation of a predictive model. To address this, feature selection methods are used to extract biological information from a large amount of data in order to filter the expression dataset down to the smallest possible subset of accurate predictor genes. Feature selection has three main advantages: it decreases computational costs, mitigates the possibility of overfitting due to high inter-variable correlations, and allows for an easier clinical interpretation of the model. In this paper we compare three methods of feature selection: iterative Bayesian Model Averaging (BMA), Random Survival Forest (RSF) and Cox Proportional Hazard (CPH) and five methods of survival analysis: Analysis RandomSurvival Forest (RSF), Cox Proportional Hazard (CPH), Alan Additive Filter (AAF), DeepSurv (neural network), andCbrSurv (case-based reasoning), which we introduce in this paper. Features selected by these methods are compared with a hand selected set of features. All the data we used came from the Metabric breast cancer dataset. Our results indicate that feature selection improves the performance of survival analysis methods. Overall, the best survival analysis performance was obtained by combining RSF for feature selection and CbrSurv, closely followed by DeepSurv, for survival prediction

Case-based reasoning (CBR) is an artificial intelligence problem solving and learning methodology that retrieves and adapts previous experiences to fit newly encountered situations. This special track, currently in its 18th year, serves as an annual forum for researchers to present and discuss developments in CBR theory and application. Mirroring the annual International Conference on Case-Based Reasoning, this year’s special track has attracted a variety of high-quality submissions that present many valuable theoretical contributions and application domains. Although the CBR special track serves an important role as a focal point for the North American CBR community, this year continues the tradition of strong international participation. We would like to thank everyone who contributed to the success of this special track, especially the authors, the program committee members, the additional reviewers, and the FLAIRS conference organizers.

Artificial Intelligence (AI) techniques are essential to the modeling of realistic behaviors for agents in simulation systems. Although Case-Based Reasoning (CBR) and Clustering techniques are being explored in the implementation of such agents in computer games, these techniques are still under-used in the implementation of simulation systems. This work approaches this gap by proposing a new CBR and clustering framework in which clustering algorithms and clustering evaluation techniques are explored in both the construction of adjusted similarity functions and the organization of sub-case bases, which are indexing components to the efficient retrieval of relevant cases from case bases so as to support the solution of new simulation problems. To evaluate this framework, a case-based algorithm was implemented to simulate the choice of military supplies to be used in artillery battery missions in virtual tactical simulations.

In this paper we present the Creative Invention Benchmark (CrIB), a 2000-problem benchmark for evaluating a particular facet of computational creativity. Specifically, we address combinational p-creativity, the creativity at play when someone combines existing knowledge to achieve a solution novel to that individual.

Today, the amount of data that can be retrieved from communications networks is extremely high and diverse (e.g., data regarding users behavior, traffic traces, network alarms, signal quality indicators, etc.). Advanced mathematical tools are required to extract useful information from this large set of network data. In particular, Machine Learning (ML) is regarded as a promising methodological area to perform network-data analysis and enable, e.g., automatized network self-configuration and fault management. In this survey we classify and describe relevant studies dealing with the applications of ML to optical communications and networking. Optical networks and system are facing an unprecedented growth in terms of complexity due to the introduction of a huge number of adjustable parameters (such as routing configurations, modulation format, symbol rate, coding schemes, etc.), mainly due to the adoption of, among the others, coherent transmission/reception technology, advanced digital signal processing and to the presence of nonlinear effects in optical fiber systems. Although a good number of research papers have appeared in the last years, the application of ML to optical networks is still in its early stage. In this survey we provide an introductory reference for researchers and practitioners interested in this field. To stimulate further work in this area, we conclude the paper proposing new possible research directions.

Reasoning is a crucial part of natural language argumentation. To comprehend an argument, one must analyze its warrant, which explains why its claim follows from its premises. As arguments are highly contextualized, warrants are usually presupposed and left implicit. Thus, the comprehension does not only require language understanding and logic skills, but also depends on common sense. In this paper we develop a methodology for reconstructing warrants systematically. We operationalize it in a scalable crowdsourcing process, resulting in a freely licensed dataset with warrants for 2k authentic arguments from news comments. On this basis, we present a new challenging task, the argument reasoning comprehension task. Given an argument with a claim and a premise, the goal is to choose the correct implicit warrant from two options. Both warrants are plausible and lexically close, but lead to contradicting claims. A solution to this task will define a substantial step towards automatic warrant reconstruction. However, experiments with several neural attention and language models reveal that current approaches do not suffice.

One of my super nerdy interests include approximate algorithms for nearest neighbors in high-dimensional spaces. You have say 1M points in some high-dimensional space. Now given a query point, can you find the nearest points out of the 1M set? Doing this fast turns out to be tricky. I'm the author of Annoy which has more than 3,000 stars on Github.

We analyze the Kozachenko--Leonenko (KL) nearest neighbor estimator for the differential entropy. We obtain the first uniform upper bound on its performance over H\"older balls on a torus without assuming any conditions on how close the density could be from zero. Accompanying a new minimax lower bound over the H\"older ball, we show that the KL estimator is achieving the minimax rates up to logarithmic factors without cognizance of the smoothness parameter $s$ of the H\"older ball for $s\in (0,2]$ and arbitrary dimension $d$, rendering it the first estimator that provably satisfies this property.