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.
This paper proposes a method to embed teacher knowledge into a student network without increasing parameters.
Framework learns portable representations for diverse tasks.
A method distills GANs for mobile devices, reducing computation and storage.
Deep Convolutional Neural Networks (DCNNs) are currently popular in human activity recognition applications. However, in the face of modern artificial intelligence sensor-based games, many research achievements cannot be practically applied on portable devices. DCNNs are typically resource-intensive and too large to be…
Paper analyzes GPS data to identify POIs and user similarities.
Relay simplifies deep learning compilation across diverse hardware.
A low-cost, robust, and simple mechanism to measure hemoglobin would play a critical role in the modern health infrastructure. Consistent sample acquisition has been a long-standing technical hurdle for photometer-based portable hemoglobin detectors which rely on micro cuvettes and dry chemistry. Any particulates (e.g.…
CodeReef enables sharing ML models across platforms efficiently.
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…
Improved malware detection by adding auxiliary loss terms to a neural network.
Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems. However, training models directly with coarsely quantized weights is a key step towa…
Deep neural networks bring in impressive accuracy in various applications, but the success often relies on the heavy network architecture. Taking well-trained heavy networks as teachers, classical teacher-student learning paradigm aims to learn a student network that is lightweight yet accurate. In this way, a portable…
Improved particle-flow event reconstruction for future colliders using scalable neural networks.
We provide complete source code for building a fundamental industry classification based on publically available and freely downloadable data. We compare various fundamental industry classifications by running a horserace of short-horizon trading signals (alphas) utilizing open source heterotic risk models (https://ssr…
Deep learning detects pneumonia with 36x compression on low-power devices.
New method quantizes neural networks for mobile devices.
Research explores how to make models more robust to adversarial attacks.
Method generates adversarial examples to improve classifier robustness.
New attacks exploit neural network energy and latency, increasing costs by 10-200x.
Automated VOC classification using embedded machine learning.
DAFL learns efficient neural networks without training data.
A simple encoder and complex decoder for secure image encryption and decryption.
Deep learning has delivered its powerfulness in many application domains, especially in image and speech recognition. As the backbone of deep learning, deep neural networks (DNNs) consist of multiple layers of various types with hundreds to thousands of neurons. Embedded platforms are now becoming essential for deep le…
New method reduces fine-tuning cost for reused models.
Framework simplifies AI access for all.
Recurrent neural networks have achieved excellent performance in many applications. However, on portable devices with limited resources, the models are often too large to deploy. For applications on the server with large scale concurrent requests, the latency during inference can also be very critical for costly comput…
In portable, 3-D, or ultra-fast ultrasound (US) imaging systems, there is an increasing demand to reconstruct high quality images from limited number of data. However, the existing solutions require either hardware changes or computationally expansive algorithms. To overcome these limitations, here we propose a novel d…
It is shown that certain diffeomorphism or homeomorphism groups with no restriction on support of an open manifold with finite number of ends are bounded. It follows that these groups are uniformly perfect. In order to characterize the boundedness several conditions on automorphism groups of an open manifold are introd…
Forward inference techniques such as sequential Monte Carlo and particle Markov chain Monte Carlo for probabilistic programming can be implemented in any programming language by creative use of standardized operating system functionality including processes, forking, mutexes, and shared memory. Exploiting this we have …
CK simplifies ML model deployment and reproducibility with open APIs and DevOps.
Simplified EEG analysis improves Parkinson's disease detection.
Malware is constantly adapting in order to avoid detection. Model based malware detectors, such as SVM and neural networks, are vulnerable to so-called adversarial examples which are modest changes to detectable malware that allows the resulting malware to evade detection. Continuous-valued methods that are robust to a…
Paper proposes a method to compress deep learning models using PU setting and cloud data.
ECC compresses DNNs for energy-constrained devices like UAVs and smartphones.
As the Portable Document Format (PDF) file format increases in popularity, research in analysing its structure for text extraction and analysis is necessary. Detecting headings can be a crucial component of classifying and extracting meaningful data. This research involves training a supervised learning model to detect…
Deep learning models accurately recognize and estimate physical activity types and energy expenditure from wrist accelerometer data.
SWALP averages SGD iterates for low-precision training, improving scalability and performance.
DataLearner simplifies data mining on Android devices.
Study explores cyberbullying datasets and classifier generalization.
We design, conduct and present the results of a highly personalized baseline emotion recognition experiment, which aims to set reliable ground-truth estimates for the subject's emotional state for real-life prediction under similar conditions using a small number of physiological sensors. We also propose an adaptive st…
Predicting the number of clock cycles a processor takes to execute a block of assembly instructions in steady state (the throughput) is important for both compiler designers and performance engineers. Building an analytical model to do so is especially complicated in modern x86-64 Complex Instruction Set Computer (CISC…
SOL is an open-source library for scalable online learning algorithms, and is particularly suitable for learning with high-dimensional data. The library provides a family of regular and sparse online learning algorithms for large-scale binary and multi-class classification tasks with high efficiency, scalability, porta…
A simple CNN architecture outperforms complex ones in P300 detection.
This work proposes a complete 8-bit quantization framework for large-scale deep neural networks.
Fuzzy hashes learn from data to improve file similarity detection.
We introduce an innovative theoretical framework to model derivative transactions between defaultable entities based on the principle of arbitrage freedom. Our framework extends the traditional formulations based on Credit and Debit Valuation Adjustments (CVA and DVA). Depending on how the default contingency is accoun…
AR-GANs learn depth and DoF from unlabeled images using aperture rendering and focus cues.
We propose a network independent, hand-held system to translate and disambiguate foreign restaurant menu items in real-time. The system is based on the use of a portable multimedia device, such as a smartphones or a PDA. An accurate and fast translation is obtained using a Machine Translation engine and a context-speci…