arXiv research

This paper analyzes sound event detection in synthetic office audio, comparing different systems.

Enhances ASC using time- and frequency-liked CNNs and bilinear pooling.

DCASE 2022 Task 2 tackles domain shifts in ASD for machine condition monitoring.

Improved performance in classifying domestic activities.

DCASE 2021 ASD task tackles domain-shifted anomalous sound detection.

Study improves CNNs for audio scene classification by restricting receptive fields and adding frequency awareness.

Task describes tagging audio clips from 41 categories.

CNNs improve generalization to unseen audio devices with increased width, not depth.

A new method detects anomalous sounds using self-supervised learning.

Paper improves sound event detection using semi-supervised learning.

Improved acoustic scene classification with factorized CNN.

New dataset for industrial machine malfunction detection with domain shifts.

This is the Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), which was held in New York, NY, June 23, 2016. Invited speakers were Susan Athey, Rich Caruana, Jacob Feldman, Percy Liang, and Hanna Wallach.

This is the Proceedings of NIPS 2016 Workshop on Interpretable Machine Learning for Complex Systems, held in Barcelona, Spain on December 9, 2016

Paper proposes MTL for weakly labelled SED, improving performance with 2-step attention.

Corrects conditions in Fissler and Ziegel's 2016 paper.

System tackles indeterminacies in automated audio captioning.

This is the Proceedings of the ICML Workshop on #Data4Good: Machine Learning in Social Good Applications, which was held on June 24, 2016 in New York.

End-to-end DA method for domain-invariant CNNs using parallel audio recordings.

The accuracy of the household electricity consumption forecast is vital in taking better cost effective and energy efficient decisions. In order to design accurate, proper and efficient forecasting model, characteristics of the series have to been analyzed. The source of time series data comes from Online Enerjisa Syst…

We present proofs of classical results in Poisson geometry using techniques from Dirac geometry. This article is based on mini-courses at the Poisson summer school in Geneva, June 2016, and at the workshop "Quantum Groups and Gravity" at the University of Waterloo, April 2016.

A framework traces ideology changes on social media during the 2016 U.S. election.

Study reveals why polls were inaccurate in 2016 US election.

This paper introduces a model of environmental acoustic scenes which adopts a morphological approach by ab-stracting temporal structures of acoustic scenes. To demonstrate its potential, this model is employed to evaluate the performance of a large set of acoustic events detection systems. This model allows us to expli…

Predicting the prices of stocks at any stock market remains a quest for many investors and researchers. Those who trade at the stock market tend to use technical, fundamental or time series analysis in their predictions. These methods usually guide on trends and not the exact likely prices. It is for this reason that A…

Weight normalization and reparametrized gradient descent adaptively regularize weights and converge to minimum l2 norm solutions.

DVAE++ uses overlapping distributions to train discrete latent variables.

In the present paper we prove Liouville-type theorems: non-existence theorems for conformal mappings of complete Riemannian manifolds. In addition, we give an application of these results to the theory of conharmonic transformations. A part of these results was announced in our reports on the conferences "Differential …

Paper discusses ASD challenge for machine condition monitoring.

This is a write-up of the author's talk in the conference "Algebraic Geometry in East Asia 2016" held at the University of Tokyo in January 2016. We give a survey on a series of papers of the author and his collaborators Daniel Pomerleano and Kazushi Ueda where we show how Strominger-Yau-Zaslow (SYZ) transforms can be …

We refute Taleb's claim that election forecasts are arbitrage-violating.

This research evaluates the performance of an Artificial Neural Network based prediction system that was employed on the Shanghai Stock Exchange for the period 21-Sep-2016 to 11-Oct-2016. It is a follow-up to a previous paper in which the prices were predicted and published before September 21. Stock market price predi…

NIPS 2016 analyzed its review process to improve future conferences.

We describe the 1st place winning approach for the CIKM Cup 2016 Challenge. In this paper, we provide an approach to reasonably identify same users across multiple devices based on browsing logs. Our approach regards a candidate ranking problem as pairwise classification and utilizes an unsupervised neural feature ense…

This paper presents the Intelligent Voice (IV) system submitted to the NIST 2016 Speaker Recognition Evaluation (SRE). The primary emphasis of SRE this year was on developing speaker recognition technology which is robust for novel languages that are much more heterogeneous than those used in the current state-of-the-a…

Self-supervised attention model improves weakly labeled audio event classification.

Chernozhukov, Chetverikov, Demirer, Duflo, Hansen, and Newey (2016) provide a generic double/de-biased machine learning (DML) approach for obtaining valid inferential statements about focal parameters, using Neyman-orthogonal scores and cross-fitting, in settings where nuisance parameters are estimated using a new gene…

The paper proves formulas for capillary surfaces and applies them to inequalities and area estimates.

Mutual info trees show higher risk in Brazilian equity network during transition.

Improves Graph Convolutional Network performance on citation datasets.

Between 2003 and 2015 the prices of apartments in Hong Kong (adjusted for inflation) increased by a factor of 3.8. This is much higher than in the United States prior to the so-called subprime crisis of 2007. The analysis of this speculative episode confirms the mechanism and regularities already highlighted by the pre…

Data analysis with log-periodical parametrization of the Brent oil price dynamics has allowed to estimate (very approximately) the date when the dashing collapse of the Brent oil price will achieve the absolute minimum level (corresponding to the so-called singularity point), after which there will occur a rather rapid…

This is an expanded version of the lecture course the second author gave at Winterbraids VI in Lille in February 2016. Version 2: revision incorporating referee remarks.

In [Tohoku Math. J. 62 (2010), 45--53] the second author showed that, except for a few cases, the order $N$ of a cyclic group of self-homeomorphisms of a closed orientable topological surface $S_g$ of genus $g \geq 2$ determines the group up to a topological conjugation, provided that $N\geq 3g$. The first author et al…

Paper predicts house prices in major Chinese cities using LSTM networks.

In recent times, the use of separable convolutions in deep convolutional neural network architectures has been explored. Several researchers, most notably (Chollet, 2016) and (Ghosh, 2017) have used separable convolutions in their deep architectures and have demonstrated state of the art or close to state of the art pe…

We consider two stage estimation with a non-parametric first stage and a generalized method of moments second stage, in a simpler setting than (Chernozhukov et al. 2016). We give an alternative proof of the theorem given in (Chernozhukov et al. 2016) that orthogonal second stage moments, sample splitting and $n^{1/4}$-…

We give a complete classification of conformally covariant differential operators between the spaces of $i$-forms on the sphere $S^n$ and $j$-forms on the totally geodesic hypersphere $S^{n-1}$. Moreover, we find explicit formulæ for these new matrix-valued operators in the flat coordinates in terms of basic operators …