Computer Science - Artificial Intelligence Publications (10)


Computer Science - Artificial Intelligence Publications

Catastrophic forgetting is a problem which refers to losing the information of the first task after training from the second task in continual learning of neural networks. To resolve this problem, we propose the incremental moment matching (IMM), which uses the Bayesian neural network framework. IMM assumes that the posterior distribution of parameters of neural networks is approximated with Gaussian distribution and incrementally matches the moment of the posteriors, which are trained for the first and second task, respectively. Read More

Although information workers may complain about meetings, they are an essential part of their work life. Consequently, busy people spend a significant amount of time scheduling meetings. We present Calendar. Read More

We extend the $ASPIC^+$ framework for structured argumentation so as to allow applications of the reasoning by cases inference scheme for defeasible arguments. Given an argument with conclusion `$A$ or $B$', an argument based on $A$ with conclusion $C$, and an argument based on $B$ with conclusion $C$, we allow the construction of an argument with conclusion $C$. We show how our framework leads to different results than other approaches in non-monotonic logic for dealing with disjunctive information, such as disjunctive default theory or approaches based on the OR-rule (which allows to derive a defeasible rule `If ($A$ or $B$) then $C$', given two defeasible rules `If $A$ then $C$' and `If $B$ then $C$'). Read More

A recurring problem faced when training neural networks is that there is typically not enough data to maximize the generalization capability of deep neural networks(DNN). There are many techniques to address this, including data augmentation, dropout, and transfer learning. In this paper, we introduce an additional method which we call Smart Augmentation and we show how to use it to increase the accuracy and reduce overfitting on a target network. Read More

As a general and thus popular model for autonomous systems, partially observable Markov decision process (POMDP) can capture uncertainties from different sources like sensing noises, actuation errors, and uncertain environments. However, its comprehensiveness makes the planning and control in POMDP difficult. Traditional POMDP planning problems target to find the optimal policy to maximize the expectation of accumulated rewards. Read More

This paper presents a statistical method for music transcription that can estimate score times of note onsets and offsets from polyphonic MIDI performance signals. Because performed note durations can deviate largely from score-indicated values, previous methods had the problem of not being able to accurately estimate offset score times (or note values) and thus could only output incomplete musical scores. Based on observations that the pitch context and onset score times are influential on the configuration of note values, we construct a context-tree model that provides prior distributions of note values using these features and combine it with a performance model in the framework of Markov random fields. Read More

Knowledge bases of real-world facts about entities and their relationships are useful resources for a variety of natural language processing tasks. However, because knowledge bases are typically incomplete, it is useful to be able to perform knowledge base completion, i.e. Read More