A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New insights suggest larger early layers improve CNN performance.
Feature noise causes loss discrepancies across groups even with equal data.
Proposes a curriculum-based scheme to smooth CNN feature embeddings.
Deep learning improves ECG arrhythmia classification.
Study of local optima in neural networks for feature interactions.
Network Lasso classifies partially labeled data with high-dimensional features.
A new method selects features efficiently for high-dimensional data.
We propose a spatial diffuseness feature for deep neural network (DNN)-based automatic speech recognition to improve recognition accuracy in reverberant and noisy environments. The feature is computed in real-time from multiple microphone signals without requiring knowledge or estimation of the direction of arrival, an…
The amount of information in the form of features and variables avail- able to machine learning algorithms is ever increasing. This can lead to classifiers that are prone to overfitting in high dimensions, high di- mensional models do not lend themselves to interpretable results, and the CPU and memory resources necess…
Improved CTR prediction with XDBoost neural network.
Deep linear networks exhibit collapsing features and classifiers across datasets.
Paper proposes using DMD for feature extraction in image classification.
Many methods have been proposed for community detection in networks, but most of them do not take into account additional information on the nodes that is often available in practice. In this paper, we propose a new joint community detection criterion that uses both the network edge information and the node features to…
We propose a method to classify cardiac pathology based on a novel approach to extract image derived features to characterize the shape and motion of the heart. An original semi-supervised learning procedure, which makes efficient use of a large amount of non-segmented images and a small amount of images segmented manu…
Sequence feature embedding is a challenging task due to the unstructuredness of sequence, i.e., arbitrary strings of arbitrary length. Existing methods are efficient in extracting short-term dependencies but typically suffer from computation issues for the long-term. Sequence Graph Transform (SGT), a feature embedding …
BSF algorithm reduces neural network size and selects features efficiently.
A new framework for generating predictive features in noisy multivariate time series.
Top-down information plays a central role in human perception, but plays relatively little role in many current state-of-the-art deep networks, such as Convolutional Neural Networks (CNNs). This work seeks to explore a path by which top-down information can have a direct impact within current deep networks. We explore …
New RL difficulty shown for discounted settings.
In recent years, deep learning algorithms have become increasingly more prominent for their unparalleled ability to automatically learn discriminant features from large amounts of data. However, within the field of electromyography-based gesture recognition, deep learning algorithms are seldom employed as they require …
Many efforts have been made to use various forms of domain knowledge in malware detection. Currently there exist two common approaches to malware detection without domain knowledge, namely byte n-grams and strings. In this work we explore the feasibility of applying neural networks to malware detection and feature lear…
This work proves convergence of adaptive resampling for random Fourier features.
Large-scale surveys make huge amounts of photometric data available. Because of the sheer amount of objects, spectral data cannot be obtained for all of them. Therefore it is important to devise techniques for reliably estimating physical properties of objects from photometric information alone. These estimates are nee…
In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance…
In the domain of technology startups, biotechnology has often been considered as specific. Their unique technology content, the type of founders and managers they have, the amount of venture capital they raise, the time it takes them to reach an exit as well as the technology clusters they belong to are seen as such un…
During the last decade, a considerable amount of effort has been made to classify variable stars using different machine learning techniques. Typically, light curves are represented as vectors of statistical descriptors or features that are used to train various algorithms. These features demand big computational power…
Low power digital signal processors (DSPs) typically have a very limited amount of memory in which to cache data. In this paper we develop efficient bottleneck feature (BNF) extractors that can be run on a DSP, and retrain a baseline large-vocabulary continuous speech recognition (LVCSR) system to use these BNFs with o…
Novel graph-based framework for hyperspectral image classification using superpixels.
We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches. (i) It automatically derives a compact, sparse and meaningful feature representation of sensor data that does not rely on prior expert know…
We consider the problem of object recognition with a large number of classes. In order to overcome the low amount of labeled examples available in this setting, we introduce a new feature learning and extraction procedure based on a factor model we call spike-and-slab sparse coding (S3C). Prior work on S3C has not prio…
Convolutional neural networks provide visual features that perform remarkably well in many computer vision applications. However, training these networks requires significant amounts of supervision. This paper introduces a generic framework to train deep networks, end-to-end, with no supervision. We propose to fix a se…
Proposes a semi-supervised K-Means algorithm for better feature selection.
Proposes ACLAE-DT for unsupervised anomaly detection in multivariate time series.
Enhances machine learning with background knowledge through feature generation.
Self-supervised learning boosts HAR performance with minimal labeled data.
Machine Learning (ML) is increasingly being used for computer aided diagnosis of brain related disorders based on structural magnetic resonance imaging (MRI) data. Most of such work employs biologically and medically meaningful hand-crafted features calculated from different regions of the brain. The construction of su…
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source domain}. It can be expensive or even infeasible to obtain required amount of lab…
SLEIPNIR improves Gaussian process regression with derivatives, scaling up efficiently and accurately.
Macrocanonical models generate textures matching input features.
VAE improves semi-supervised learning in small data.
In this paper we present a technique for using the bootstrap to estimate the operating characteristics and their variability for certain types of ensemble methods. Bootstrapping a model can require a huge amount of work if the training data set is large. Fortunately in many cases the technique lets us determine the eff…
In an era where accumulating data is easy and storing it inexpensive, feature selection plays a central role in helping to reduce the high-dimensionality of huge amounts of otherwise meaningless data. In this paper, we propose a graph-based method for feature selection that ranks features by identifying the most import…
We consider the problem of classifying business process instances based on structural features derived from event logs. The main motivation is to provide machine learning based techniques with quick response times for interactive computer assisted root cause analysis. In particular, we create structural features from p…
Sparse GEMINI selects relevant features for clustering without assumptions.
A federated model predicts failures using multi-stream incomplete data.
Deep learning models misclassify malware with added benign features.
We introduce and study a simple model of a limit order-driven market. Traders in this model can either trade at the market price or place a limit order, i.e. an instruction to buy (sell) a certain amount of the stock if its price falls below (raises above) a predefined level. The choice between these two options is pur…
Data collection is a major bottleneck in machine learning and an active research topic in multiple communities. There are largely two reasons data collection has recently become a critical issue. First, as machine learning is becoming more widely-used, we are seeing new applications that do not necessarily have enough …