bookmarks (hide)24
- 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.
- Artificial intelligence (AI) and robotics are major breakthrough technologies that are transforming the economy and society. To understand and anticipate this transformation, policy makers must first understand what these technologies can and cannot do. The OECD launched the Artificial Intelligence and the Future of Skills project to develop a programme that could assess the capabilities of AI and robotics and their impact on education and work. This report represents the first step in developing the methodological approach of the project. It reviews existing taxonomies and tests in psychology and computer science, and discusses their strengths, weaknesses and applicability for assessing machine capabilities. OECD iLibrary
- The era of Artificial Intelligence is a human challenge of the greatest of the future. From its proper management and control the foundations will be born, which must be firm and legislated, which will form a safe and technological tomorrow. | https://editorialia.com/ | ISSN 2695-6411|
- «AutoQML, self-assembling circuits, hyper-parameterized Quantum ML platform, using cirq, tensorflow and tfq. Trillions of possible qubit registries, gate combinations and moment sequences, ready to be adapted into your ML flow. Here I demonstrate climatechange, jameswebbspacetelescope and microbiology vision applications… [Thus far, a circuit with 16-Qubits and a gate sequence of [ YY ] – [ XX ] – [CNOT] has performed the best, per my blend of metrics…]».
- «What are the units of text that we want to model? From bytes to multi-word expressions, text can be analyzed and generated at many granularities. Until recently, most natural language processing (NLP) models operated over words, treating those as discrete and atomic tokens, but starting with byte-pair encoding (BPE), subword-based approaches have become dominant in many areas, enabling small vocabularies while still allowing for fast inference. Is the end of the road character-level model or byte-level processing? In this survey, we connect several lines of work from the pre-neural and neural era, by showing how hybrid approaches of words and characters as well as subword-based approaches based on learned segmentation have been proposed and evaluated. We conclude that there is and likely will never be a silver bullet singular solution for all applications and that thinking seriously about tokenization remains important for many applications.»
- Deep learning’s great success motivates many practitioners and students to learn about this exciting technology. However, it is often challenging for beginners to take their first step due to the complexity of understanding and applying deep learning. We present CNN Explainer, an interactive visualization tool designed for non-experts to learn and examine convolutional neural networks (CNNs), a foundational deep learning model architecture. Our tool addresses key challenges that novices face while learning about CNNs, which we identify from interviews with instructors and a survey with past students. CNN Explainer tightly integrates a model overview that summarizes a CNN’s structure, and on-demand, dynamic visual explanation views that help users understand the underlying components of CNNs. Through smooth transitions across levels of abstraction, our tool enables users to inspect the interplay between low-level mathematical operations and high-level model structures. A qualitative user study shows that CNN Explainer helps users more easily understand the inner workings of CNNs, and is engaging and enjoyable to use. We also derive design lessons from our study. Developed using modern web technologies, CNN Explainer runs locally in users’ web browsers without the need for installation or specialized hardware, broadening the public’s education access to modern deep learning techniques.
- ««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 study the ramifications for spatial localization, demonstrating ViTs successfully preserve input spatial information, with noticeable effects from different classification methods. Finally, we study the effect of (pretraining) dataset scale on intermediate features and transfer learning, and conclude with a discussion on connections to new architectures such as the MLP-Mixer.»
- «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. In previous work, we proposed that ethics-based auditing (EBA)—that is, a structured process by which ADMS are assessed for consistency with relevant principles or norms—can (a) help organisations verify claims about their ADMS and (b) provide decision-subjects with justifications for the outputs produced by ADMS. In this article, we outline the conditions under which EBA procedures can be feasible and effective in practice. First, we argue that EBA is best understood as a ‘soft’ yet ‘formal’ governance mechanism. This implies that the main responsibility of auditors should be to spark ethical deliberation at key intervention points throughout the software development process and ensure that there is sufficient documentation to respond to potential inquiries. Second, we frame AMDS as parts of larger sociotechnical systems to demonstrate that to be feasible and effective, EBA procedures must link to intervention points that span all levels of organisational governance and all phases of the software lifecycle. The main function of EBA should, therefore, be to inform, formalise, assess, and interlink existing governance structures. Finally, we discuss the policy implications of our findings. To support the emergence of feasible and effective EBA procedures, policymakers and regulators could provide standardised reporting formats, facilitate knowledge exchange, provide guidance on how to resolve normative tensions, and create an independent body to oversee EBA of ADMS.»
- 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. Combined with Featuretools and Compose, EvalML can be used to create end-to-end supervised machine learning solutions. “EvalML provides a simple, unified interface for building machine learning models, using those models to generate insights and to make accurate predictions. EvalML provides access to multiple modeling libraries under the same API. EvalML supports a variety of supervised machine learning problem types including regression, binary classification and multiclass classification. Custom objective functions let users phrase their search for a model directly in terms of what they value. Above all we’ve aimed to make EvalML stable and performant, with ML performance testing on every release”
- «Since the federated learning, which makes AI learning possible without moving local data around, was introduced by google in 2017 it has been actively studied particularly in the field of medicine. In fact, the idea of machine learning in AI without collecting data from local clients is very attractive because data remain in local sites. However, federated learning techniques still have various open issues due to its own characteristics such as non identical distribution, client participation management, and vulnerable environments. In this presentation, the current issues to make federated learning flawlessly useful in the real world will be briefly overviewed. They are related to data/system heterogeneity, client management, traceability, and security. Also, we introduce the modularized federated learning framework, we currently develop, to experiment various techniques and protocols to find solutions for aforementioned issues. The framework will be open to public after development completes».
- “This guide is designated to anybody with basic programming knowledge or a computer science background interested in becoming a Research Scientist with on Deep Learning and NLP”.
- «Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort the structures of around 100,000 unique proteins have been determined, but this represents a small fraction of the billions of known protein sequences. Structural coverage is bottlenecked by the months to years of painstaking effort required to determine a single protein structure. Accurate computational approaches are needed to address this gap and to enable large-scale structural bioinformatics. Predicting the three-dimensional structure that a protein will adopt based solely on its amino acid sequence—the structure prediction component of the ‘protein folding problem’—has been an important open research problem for more than 50 years. Despite recent progress existing methods fall far short of atomic accuracy, especially when no homologous structure is available. Here we provide the first computational method that can regularly predict protein structures with atomic accuracy even in cases in which no similar structure is known. We validated an entirely redesigned version of our neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14), demonstrating accuracy competitive with experimental structures in a majority of cases and greatly outperforming other methods. 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.»
- 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
- Machine learning covers a lot of ground but it is also capable of making bad decision. We’ve also reached a stage of hype that folks forget that many classification problems can be handled by natural intelligence too. This package contains scikit-learn compatible tools that should make it easier to construct and benchmark rule based systems that are designed by humans. You can also use it in combination with ML models
- Objective “I was emboldened to write this book after my video series called Data Science With Julia got some traction. That too after a tweet about Decision Tree was liked by Julia Language itself. So I thought why not give it more? This book should be seen as my attempt to explain Data Science to my self and nothing more. Will this book rise to professional stature is yet to be seen.”
- Isaac Gym offers a high performance learning platform to train policies for wide variety of robotics tasks directly on GPU. Both physics simulation and the neural network policy training reside on GPU and communicate by directly passing data from physics buffers to PyTorch tensors without ever going through any CPU bottlenecks. This leads to blazing fast training times for complex robotics tasks on a single GPU with 2-3 orders of magnitude improvements compared to conventional RL training that uses a CPU based simulator and GPU for neural networks.
- 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. The proposed algorithm consists of three parts: an imaginative model for anticipating results before parking, an improved rapid-exploring random tree (RRT) for planning a feasible trajectory from a given start point to a parking lot, and a path smoothing module for optimizing the efficiency of parking tasks. Our algorithm is based on a real kinematic vehicle model; which makes it more suitable for algorithm application on real autonomous cars. Furthermore, due to the introduction of the imagination mechanism, the processing speed of our algorithm is ten times faster than that of traditional methods, permitting the realization of real-time planning simultaneously. In order to evaluate the algorithm’s effectiveness, we have compared our algorithm with traditional RRT, within three different parking scenarios. Ultimately, results show that our algorithm is more stable than traditional RRT and performs better in terms of efficiency and quality.
- «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 take finite difference method to discretize NPDE for finding numerical solution, and the basic building blocks of deep neural network architecture, including multi-layer perceptron, convolutional neural network and recurrent neural networks, are generated. The learning strategies, such as Adaptive moment estimation, L-BFGS, pseudoinverse learning algorithms and partial differential equation constrained optimization, are also presented. We believe it is of significance that presented clear physical image of interpretable deep neural networks, which makes it be possible for applying to analog computing device design, and pave the road to physical artificial intelligence».
- Europe: «The Commission is proposing the first ever legal framework on AI, which addresses the risks of AI and positions Europe to play a leading role globally»
- «This book is organized into four parts. The first part considers the fundamental principles of the Matplotlib library. This includes reviewing the different parts that constitute a figure, the different coordinate systems, the available scales and projections, and we’ll also introduce a few concepts related to typography and colors. The second part is dedicated to the actual design of a figure. After introducing some simple rules for generating better figures, we’ll then go on to explain the Matplotlib defaults and styling system before diving on into figure layout organization. We’ll then explore the different types of plot available and see how a figure can be ornamented with different elements. The third part is dedicated to more advanced concepts, namely 3D figures, optimization & animation. The fourth and final part is a collection of showcases.»
publications
(hide)13
This list of posts may not be accurate to recent changes. If you want accurate posts, but with limited sorting follow this link.
- IA eñ ™, (July 2021)
- The Bible of AI ™ OpenScience, (June 2021)
- The Bible of AI ™ OpenScience, (2022)
- (March 2022)
- IA eñ ™, (March 2021)
- The Bible of AI ™ OpenScience, (August 2021)
- The Bible of AI ™ OpenScience, (December 2021)
- IAeñ, (November 2021)
- IA eñ TM, (May 2022)https://www.itvia.online/pub/la-importancia-de-la-entonacion-y-el-contexto-en-los-traductores-pln-basados-en-inteligencia-artificial.
- IA eñ ™, (May 2021)
- IAeñ, (March 2022)
- The Bible of AI ™ OpenScience, (March 2021)
- (June 2022)
