SELECT PROFILE down
Ethics-based auditing of automated decision-making systems: intervention points and policy implications
Organisations increasingly use automated decision-making systems (ADMS) to inform decisions that affect humans and their environment. While the use of ADMS can improve the accuracy and efficiency of decision-making processes, it is also coupled with ethical challenges. Unfortunately, the governance mechanisms currently used to oversee human decision-making often fail when applied to ADMS.
Convolutional neural networks (CNNs) have so far been the de-facto model for visual data. Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or even superior performance on image classification tasks. This raises a central question: how are Vision Transformers solving these tasks? Are they acting like convolutional networks, or learning entirely different visual representations? Analyzing the internal representation structure of ViTs and CNNs on image classification benchmarks, we find striking differences between the two architectures, such as ViT having more uniform representations across all layers. We explore how these differences arise, finding crucial roles played by self-attention, which enables early aggregation of global information, and ViT residual connections, which strongly propagate features from lower to higher layers.
We analyze the math fundamentals behind DP and demonstrate the power of it by applying it on two real-world text classification tasks. Furthermore, we compare DP with pointillistic active and semi-supervised learning techniques traditionally applied in data-sparse settings.
Underpinning the latest version of AlphaFold is a novel machine learning approach that incorporates physical and biological knowledge about protein structure, leveraging multi-sequence alignments, into the design of the deep learning algorithm.
Autonomous parking technology is a key concept within autonomous driving research. This paper will propose an imaginative autonomous parking algorithm to solve issues concerned with parking.
CARLA (Counterfactual And Recourse LibrAry), a python library for benchmarking counterfactual explanation methods across both different data sets and different machine learning models. In summary, our work provides the following contributions: (i) an extensive benchmark of 11 popular counterfactual explanation methods, (ii) a benchmarking framework for research on future counterfactual explanation methods, and (iii) a standardized set of integrated evaluation measures and data sets for transparent and extensive comparisons of these methods. We have open-sourced CARLA and our experimental results on Github, making them available as competitive baselines. We welcome contributions from other research groups and practitioners.
A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning
This paper provides a succinct overview of this emerging theory of overparameterized ML (henceforth abbreviated as TOPML) that explains these recent findings through a statistical signal processing perspective. We emphasize the unique aspects that define the TOPML research area as a subfield of modern ML theory and outline interesting open questions that remain.
This document gives a concise outline of some of the common mistakes that occur when using machine learning techniques, and what can be done to avoid them. It is intended primarily as a guide for research students, and focuses on issues that are of particular concern within academic research, such as the need to do rigorous comparisons and reach valid conclusions. It covers five stages of the machine learning process: what to do before model building, how to reliably build models, how to robustly evaluate models, how to compare models fairly, and how to report results
We switch the YOLO detector to an anchor-free manner and conduct other advanced detection techniques, i.e., a decoupled head and the leading label assignment strategy SimOTA to achieve state-of-the-art results across a large scale range of models: For YOLO-Nano with only 0.91M parameters and 1.08G FLOPs, we get 25.3% AP on COCO, surpassing NanoDet by 1.8% AP; for YOLOv3, one of the most widely used detectors in industry, we boost it to 47.3% AP on COCO, outperforming the current best practice by 3.0% AP; for YOLOX-L with roughly the same amount of parameters as YOLOv4-CSP, YOLOv5-L, we achieve 50.0% AP on COCO at a speed of 68.9 FPS on Tesla V100, exceeding YOLOv5-L by 1.8% AP.
Framework based on parameterized images on ResNet to identify intrusions in smartwatches or other related devices
The continuous appearance and improvement of mobile devices in the form of smartwatches, smartphones and other similar devices has led to a growing and unfair interest in putting their users under the magnifying glass and control of applications.
A panoptic driving perception system is an essential part of autonomous driving. A high-precision and real-time perception system can assist the vehicle in making the reasonable decision while driving. We present a panoptic driving perception network (YOLOP) to perform traffic object detection, drivable area segmentation and lane detection simultaneously. It is composed of one encoder for feature extraction and three decoders to handle the specific tasks. Our model performs extremely well on the challenging BDD100K dataset, achieving state-of-the-art on all three tasks in terms of accuracy and speed. Besides, we verify the effectiveness of our multi-task learning model for joint training via ablative studies.
This is a collection of simple PyTorch implementations of neural networks and related algorithms. These implementations are documented with explanations, and the website renders these as side-by-side formatted notes. We believe these would help you understand these algorithms better.
Data as the main focus of “State of the art of data science in Spanish language and its application in the field of Artificial Intelligence”
According to the results, there is an evidence of cultural bias for data science in Spanish language. The outcome of the consultation, which carried out on 12 April 2021, confirms that only 10 out of 23.771 datasets “speaks” Spanish.”
‘Framework’ basado en imágenes parametrizadas sobre ResNet para identificar intrusiones en ‘smartwatches’ u otros dispositivos afines
La continua aparición y mejora de dispositivos móviles en forma de ‘smartwatches’, ‘smartphones’ y otros dispositivos similares ha propicio un creciente y desleal interés en poner bajo la lupa y el control de los aplicativos a sus usuarios. De forma ofuscada por los fabricantes.
Los datos como eje principal en el “Estado del arte de la ciencia de datos en el idioma español y su aplicación en el campo de la Inteligencia Artificial”
Los resultados de este estudio son una evidencia del sesgo cultural que existe entre la lengua inglesa y la española en la ciencia de datos. De los 23.771 conjuntos de datos que se encontraron con fecha de consulta 12/04/2021, tan solo 10 se encontraban en castellano
EvalML is an AutoML library that builds, optimizes, and evaluates machine learning pipelines using domain-specific objective functions, it is a library for automated machine learning (AutoML) and model understanding, written in Python
The study of art provides results that indicate the absence of involvement of Spanish language with AI and all the subareas, which consequently adversely affect to the education of future professionals.
Partial Differential Equations is All You Need for Generating Neural Architectures — A Theory for Physical Artificial Intelligence Systems
In this work, we generalize the reaction-diffusion equation in statistical physics, Schrödinger equation in quantum mechanics, Helmholtz equation in paraxial optics into the neural partial differential equations (NPDE), which can be considered as the fundamental equations in the field of artificial intelligence research
We present the federated training on hybrid quantum-classical machine learning models although our framework could be generalized to pure quantum machine learning model. Specifically, we consider the quantum neural network (QNN) coupled with classical pre-trained convolutional model.
El estado del arte de la ciencia de datos en el idioma español y su aplicación en el campo de la Inteligencia Artificial
El estudio arroja resultados que indican la falta de involucración del Español con la IA así como de todas las subáreas, afectando negativamente a la formación de futuros profesionales.
Topological Data Analysis (TDA) is an emergent field that aims to discover topological information hidden in a dataset. TDA tools have been commonly used to create filters and topological descriptors to improve Machine Learning (ML) methods. This paper proposes an algorithm that applies TDA directly to multi-class classification problems, even imbalanced datasets, without any further ML stage
One-line dataloaders for many public datasets & Efficient data pre-processing
S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Training
We introduce S++, a simple, robust, and deployable framework for training a neural network (NN) using private data from multiple sources, using secret-shared secure function evaluation. In short, consider a virtual third party to whom every data-holder sends their inputs, and which computes the neural network: in our case, this virtual third party is actually a set of servers which individually learn nothing, even with a malicious (but non-colluding) adversary.
Steganography is the science of hiding a secret message within an ordinary public message. Over the years, steganography has been used to encode a lower resolution image into a higher resolution image by simple methods like LSB manipulation. We aim to utilize deep neural networks for the encoding and decoding of multiple secret images inside a single cover image of the same resolution.
El principal objetivo de este documento es construir un glosario, a partir de las propuestas léxicas realizadas por los diferentes entes tecnológicos (ISO, IEEE, Wikipedia y Oxford University Press). Adicionalmente, el glosario estará estructurado según las ramas de conocimiento de esta área de trabajo, determinando exhaustiva y detalladamente las características de los términos que se incluirán en él para así facilitar una lectura amigable a la par que eficiente al usuario.
Something went wrong. Please refresh the page and/or try again.