SEARCH · Searcharxiv
Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
This manuscript is technical memoir about my work at Stanford and Microsoft Research. Included are fundamental concepts central to machine learning and artificial intelligence, applications of these concepts, and stories behind their creation.
In 1837, the first computer program in history was sketched by the renowned mathematician and inventor Charles Babbage. It was a program for the Analytical Engine. The program consists of a sequence of arithmetical operations and the necessary variable addresses (memory locations) of the arguments and the result, displayed in tabular fashion, like a program trace. The program computes the solutions for a system of two linear equations in two unknowns.
The development of advanced generative chat models, such as ChatGPT, has raised questions about the potential consciousness of these tools and the extent of their general artificial intelligence. ChatGPT consistent avoidance of passing the test is here overcome by asking ChatGPT to apply the Turing test to itself. This explores the possibility of the model recognizing its own sentience. In its own eyes, it passes this test. ChatGPT's self-assessment makes serious implications about our understanding of the Turing test and the nature of consciousness. This investigation concludes by considering the existence of distinct types of consciousness and the possibility that the Turing test is only effective when applied between consciousnesses of the same kind. This study also raises intriguing questions about the nature of AI consciousness and the validity of the Turing test as a means of verifying such consciousness.
This article explores the transformative impact of artificial intelligence (AI) on scientific research. It highlights ten ways in which AI is revolutionizing the work of scientists, including powerful referencing tools, improved understanding of research problems, enhanced research question generation, optimized research design, stub data generation, data transformation, advanced data analysis, and AI-assisted reporting. While AI offers numerous benefits, challenges such as bias, privacy concerns, and the need for human-AI collaboration must be considered. The article emphasizes that AI can augment human creativity in science but not replace it.
Modern computational natural philosophy conceptualizes the universe in terms of information and computation, establishing a framework for the study of cognition and intelligence. Despite some critiques, this computational perspective has significantly influenced our understanding of the natural world, leading to the development of AI systems like ChatGPT based on deep neural networks. Advancements in this domain have been facilitated by interdisciplinary research, integrating knowledge from multiple fields to simulate complex systems. Large Language Models (LLMs), such as ChatGPT, represent this approach's capabilities, utilizing reinforcement learning with human feedback (RLHF). Current research initiatives aim to integrate neural networks with symbolic computing, introducing a new generation of hybrid computational models.
Consensus on the definition of data science remains low despite the widespread establishment of academic programs in the field and continued demand for data scientists in industry. Definitions range from rebranded statistics to data-driven science to the science of data to simply the application of machine learning to so-called big data to solve real-world problems. Current efforts to trace the history of the field in order to clarify its definition, such as Donoho's "50 Years of Data Science" (Donoho 2017), tend to focus on a short period when a small group of statisticians adopted the term in an unsuccessful attempt to rebrand their field in the face of the overshadowing effects of computational statistics and data mining. Using textual evidence from primary sources, this essay traces the history of the term to the 1960s, when it was first used by the US Air Force in a surprisingly similar way to its current usage, to 2012, the year that Harvard Business Review published the enormously influential article "Data Scientist: The Sexiest Job of the 21st Century" (Davenport and Patil 2012) and the American Statistical Association acknowledged a profound disconnect between statistics and data science (Rodriguez 2012). Among the themes that emerge from this review are (1) the long-standing opposition between data analysts and data miners that continues to animate the field, (2) an established definition of the term as the practice of managing and processing scientific data that has been occluded by recent usage, and (3) the phenomenon of data impedance -- the disproportion between surplus data, indexed by phrases like data deluge and big data, and the limitations of computational machinery and methods to process them. This persistent condition appears to have motivated the use of the term and the field itself since its beginnings.
Data Science is a complex and evolving field, but most agree that it can be defined as a combination of expertise drawn from three broad areascomputer science and technology, math and statistics, and domain knowledge -- with the purpose of extracting knowledge and value from data. Beyond this, the field is often defined as a series of practical activities ranging from the cleaning and wrangling of data, to its analysis and use to infer models, to the visual and rhetorical representation of results to stakeholders and decision-makers. This essay proposes a model of data science that goes beyond laundry-list definitions to get at the specific nature of data science and help distinguish it from adjacent fields such as computer science and statistics. We define data science as an interdisciplinary field comprising four broad areas of expertise: value, design, systems, and analytics. A fifth area, practice, integrates the other four in specific contexts of domain knowledge. We call this the 4+1 model of data science. Together, these areas belong to every data science project, even if they are often unconnected and siloed in the academy.
This research provides an in-depth comprehensive review of the progress of chatbot technology over time, from the initial basic systems relying on rules to today's advanced conversational bots powered by artificial intelligence. Spanning many decades, the paper explores the major milestones, innovations, and paradigm shifts that have driven the evolution of chatbots. Looking back at the very basic statistical model in 1906 via the early chatbots, such as ELIZA and ALICE in the 1960s and 1970s, the study traces key innovations leading to today's advanced conversational agents, such as ChatGPT and Google Bard. The study synthesizes insights from academic literature and industry sources to highlight crucial milestones, including the introduction of Turing tests, influential projects such as CALO, and recent transformer-based models. Tracing the path forward, the paper highlights how natural language processing and machine learning have been integrated into modern chatbots for more sophisticated capabilities. This chronological survey of the chatbot landscape provides a holistic reference to understand the technological and historical factors propelling conversational AI. By synthesizing learnings from this historical analysis, the research offers important context about the developmental trajectory of chatbots and their immense future potential across various field of application which could be the potential take ways for the respective research community and stakeholders.
Living things, computers, societies, and even books are part of a grand evolutionary struggle to survive. That struggle shapes nature, nations, religions, art, science, and you. What you think, feel, and do is determined by it. Darwinian evolution does not apply solely to the genes that are stored in DNA. Using the insights of Alan Turing and Richard Dawkins, we will see that it also applies to the memes we store in our brains and the information we store in our computers. The next time you run for president, fight a war, or just deal with the ordinary problems humans are heir to, perhaps this book will be of use. If you want to understand why and when you will die, or if you want to achieve greatness this book may help. If you are concerned about where the computer revolution is headed, this book may provide some answers.
As we keep rapidly advancing toward an era where artificial intelligence is a constant and normative experience for most of us, we must also be aware of what this vision and this progress entail. By first approximating neural connections and activities in computer circuits and then creating more and more sophisticated versions of this crude approximation, we are now facing an age to come where modern deep learning-based artificial intelligence systems can rightly be called thinking machines, and they are sometimes even lauded for their emergent behavior and black-box approaches. But as we create more powerful electronic brains, with billions of neural connections and parameters, can we guarantee that these mammoths built of artificial neurons will be able to forget the data that we store in them? If they are at some level like a brain, can the right to be forgotten still be protected while dealing with these AIs? The essential gap between machine learning and the RTBF is explored in this article, with a premonition of far-reaching conclusions if the gap is not bridged or reconciled any time soon. The core argument is that deep learning models, due to their structure and size, cannot be expected to forget or delete a data as it would be expected from a tabular database, and they should be treated more like a mechanical brain, albeit still in development.
Rather than simply offering suggestions, this guideline for the methodology chapter in computer science dissertations provides thorough insights on how to develop a strong research methodology within the area of computer science. The method is structured into several parts starting with an overview of research strategies which include experiments, surveys, interviews and case studies. The guide highlights the significance of defining a research philosophy and reasoning by talking about paradigms such as positivism, constructivism and pragmatism. Besides, it reveals the importance of types of research including deductive and inductive methodologies; basic versus applied research approaches. Moreover, this guideline discusses data collection and analysis intricacies that divide data into quantitative and qualitative typologies. It explains different ways in which data can be collected from observation to experimentation, interviews or surveys. It also mentions ethical considerations in research emphasizing ethical behavior like following academic principles. In general, this guideline is an essential tool for undertaking computer science dissertations that help researchers structure their work while maintaining ethical standards in their study design.
It is clear, from the major press coverage that Virtual Reality (VR) development is garnering, that there is a huge amount of development interest in VR across multiple industries, including video streaming, gaming and simulated learning. Even though PC, web, and mobile are still the top platforms for software development, it is important for university computer science (CS) programs to expose students to VR as a development platform. Additionally, it is important for CS students to learn how to learn about new technologies, since change is constant in the CS field. CS curriculum changes happen much slower than the pace of technology adoption. As new technologies are introduced, CS faculty and students often learn together, especially in smaller CS programs. This paper describes how student-led VR projects are used, across the CS curriculum, as basic CS concepts are covered. The student-led VR projects are engaging, and promote learning and creativity. Additionally, each student project inspires more students to try their hand at VR development as well.
Today, symbolic mathematical computation is taken for granted as part of the scientific infrastructure, but it has not always been so. This paper provides a historical survey of the discipline's formative decade, 1965-1975, viewed from a 50 year perspective. This span of years saw the evolution from a few specialized programs with naive algorithms to integrated systems with substantial capabilities. We highlight some of the important early figures in the field and the innovations upon which the current generation of systems and algorithms are built. By revisiting a period unfamiliar to most current readers, this survey aims to shed light on once-pressing issues that are now largely resolved and to highlight how some of today's challenges were recognized earlier than expected.
Artificial intelligence (AI) has undergone remarkable development since the mid-2000s, particularly in the fields of machine learning and deep learning, driven by the explosive growth of large databases and computational capacity. Hungarian researchers recognized the significance of AI early on, actively participating in international research and achieving significant results in both theoretical and practical domains. This article presents some key achievements in Hungarian AI research. It highlights the results from the period before the rise of deep learning (the early 2010s), then discusses major theoretical advancements in Hungary after 2010. Finally, it provides a brief overview of AI-related applied scientific achievements from 2010 onward.
Context: Previous research on software aging is limited with focus on dynamic runtime indicators like memory and performance, often neglecting evolutionary indicators like source code comments and narrowly examining legacy issues within the TD context. Objective: We introduce the concept of Aging Debt (AD), representing the increased maintenance efforts and costs needed to keep software updated. We study AD through Self-Admitted Aging Debt (SAAD) observed in source code comments left by software developers. Method: We employ a mixed-methods approach, combining qualitative and quantitative analyses to detect and measure AD in software. This includes framing SAAD patterns from the source code comments after analysing the source code context, then utilizing the SAAD patterns to detect SAAD comments. In the process, we develop a taxonomy for SAAD that reflects the temporal aging of software and its associated debt. Then we utilize the taxonomy to quantify the different types of AD prevalent in OSS repositories. Results: Our proposed taxonomy categorizes temporal software aging into Active and Dormant types. Our extensive analysis of over 9,000+ Open Source Software (OSS) repositories reveals that more than 21% repositories exhibit signs of SAAD as observed from our gold standard SAAD dataset. Notably, Dormant AD emerges as the predominant category, highlighting a critical but often overlooked aspect of software maintenance. Conclusion: As software volume grows annually, so do evolutionary aging and maintenance challenges; our proposed taxonomy can aid researchers in detailed software aging studies and help practitioners develop improved and proactive maintenance strategies.
Digital ethics, also known as computer ethics or information ethics, is now a lively field that draws a lot of attention, but how did it come about and what were the developments that lead to its existence? What are the traditions, the concerns, the technological and social developments that pushed digital ethics? How did ethical issues change with digitalisation of human life? How did the traditional discipline of philosophy respond? The article provides an overview, proposing historical epochs: 'pre-modernity' prior to digital computation over data, via the 'modernity' of digital data processing to our present 'post-modernity' when not only the data is digital, but our lives themselves are largely digital. In each section, the situation in technology and society is sketched, and then the developments in digital ethics are explained. Finally, a brief outlook is provided.
In this note, we reflect on several fundamental connections among widely used post-training techniques. We clarify some intimate connections and equivalences between reinforcement learning with human feedback, reinforcement learning with internal feedback, and test-time scaling (particularly soft best-of-$N$ sampling), while also illuminating intrinsic links between diffusion guidance and test-time scaling. Additionally, we introduce a resampling approach for alignment and reward-directed diffusion models, sidestepping the need for explicit reinforcement learning techniques.
AI policymakers are responsible for delivering effective governance mechanisms that can provide safe, aligned and trustworthy AI development. However, the information environment offered to policymakers is characterised by an unnecessarily low Signal-To-Noise Ratio, favouring regulatory capture and creating deep uncertainty and divides on which risks should be prioritised from a governance perspective. We posit that the current publication speeds in AI combined with the lack of strong scientific standards, via weak reproducibility protocols, effectively erodes the power of policymakers to enact meaningful policy and governance protocols. Our paper outlines how AI research could adopt stricter reproducibility guidelines to assist governance endeavours and improve consensus on the AI risk landscape. We evaluate the forthcoming reproducibility crisis within AI research through the lens of crises in other scientific domains; providing a commentary on how adopting preregistration, increased statistical power and negative result publication reproducibility protocols can enable effective AI governance. While we maintain that AI governance must be reactive due to AI's significant societal implications we argue that policymakers and governments must consider reproducibility protocols as a core tool in the governance arsenal and demand higher standards for AI research. Code to replicate data and figures: https://github.com/IFMW01/reproducibility-the-new-frontier-in-ai-governance