We discuss the origin of multiscaling in financial time-series and investigate how to best quantify it. Our methodology consists in separating the different sources of measured multifractality by analysing the multi/uni-scaling behaviour of synthetic time-series with known properties. We use the results from the synthetic time-series to interpret the measure of multifractality of real log-returns time-series. The main finding is that the aggregation horizon of the returns can introduce a strong bias effect on the measure of multifractality. This effect can become especially important when returns distributions have power law tails with exponents in the range [2,5]. We discuss the right aggregation horizon to mitigate this bias.
A Bayesian Compressed Sensing Kalman Filter for Direction of Arrival Estimation
In this paper, we look to address the problem of estimating the dynamic direction of arrival (DOA) of a narrowband signal impinging on a sensor array from the far field. The initial estimate is made using a Bayesian compressive sensing (BCS) framework and then tracked using a Bayesian compressed sensing Kalman filter (BCSKF). The BCS framework splits the angular region into N potential DOAs and enforces a belief that only a few of the DOAs will have a non-zero valued signal present. A BCSKF can then be used to track the change in the DOA using the same framework. There can be an issue when the DOA approaches the endfire of the array. In this angular region current methods can struggle to accurately estimate and track changes in the DOAs. To tackle this problem, we propose changing the traditional sparse belief associated with BCS to a belief that the estimated signals will match the predicted signals given a known DOA change. This is done by modelling the difference between the expected sparse received signals and the estimated sparse received signals as a Gaussian distribution. Example test scenarios are provided and comparisons made with the traditional BCS based estimation method. They show that an improvement in estimation accuracy is possible without a significant increase in computational complexity.
http://arxiv.org/abs/1509.06290
In this paper, we look to address the problem of estimating the dynamic direction of arrival (DOA) of a narrowband signal impinging on a sensor array from the far field. The initial estimate is made using a Bayesian compressive sensing (BCS) framework and then tracked using a Bayesian compressed sensing Kalman filter (BCSKF). The BCS framework splits the angular region into N potential DOAs and enforces a belief that only a few of the DOAs will have a non-zero valued signal present. A BCSKF can then be used to track the change in the DOA using the same framework. There can be an issue when the DOA approaches the endfire of the array. In this angular region current methods can struggle to accurately estimate and track changes in the DOAs. To tackle this problem, we propose changing the traditional sparse belief associated with BCS to a belief that the estimated signals will match the predicted signals given a known DOA change. This is done by modelling the difference between the expected sparse received signals and the estimated sparse received signals as a Gaussian distribution. Example test scenarios are provided and comparisons made with the traditional BCS based estimation method. They show that an improvement in estimation accuracy is possible without a significant increase in computational complexity.
http://arxiv.org/abs/1509.06290
Describes stochastic gradient decent methods for large data sets estimation
Google built new neural network acoustic models using Connectionist Temporal Classification (CTC) and sequence discriminative training techniques.
http://googleresearch.blogspot.co.uk/2015/09/google-voice-search-faster-and-more.html
http://googleresearch.blogspot.co.uk/2015/09/google-voice-search-faster-and-more.html
Googleblog
Google voice search: faster and more accurate
Deep Learning Summer School videos, Montreal 2015
http://videolectures.net/deeplearning2015_montreal/
http://videolectures.net/deeplearning2015_montreal/
There is a deep learning meet up in Stockholm and they are recording videos of their meetings
Surveillance-nature images are released in the download links as "sv_data.*". Download all such files, then unzip them with the same password as the web-nature data. We also conducted a fine-grained classification experiment for this part of data. The results are provided in the arXiv paper.