Mondays and Wednesdays 1:30-3:00
Packard 101
Instructor:
Ed Question Forum: ( )
Email:
Selected Readings of CS Research examines 8 selected papers by leading scholars in computer science and electrical engineering. The papers cover a wide range of subfields within CS and EE. Students taking this course will learn about a broad view of research fields in EE and CS, including what kinds of problems different fields tackle as well as how they think about them. Students learn how to read research papers and see how different fields structure and present their ideas. Undergraduates interested in research, beginning graduate students who want to learn about how to approach publications, and more senior graduate students who want to read a selection of excellent work from a wide variety of fields are all encouraged to enroll.
Each paper has two lectures on it. The first lecture is an introductory lecture, given by the instructor or expert in the field. This introductory lecture explains the research area and context of the work, giving enough basics so everyone in the class can read and begin to understand the paper. The second lecture is by one of the faculty authors of the paper, who will talk about the paper and how it came about, discuss their career, and answer questions.
Coursework involves writing a 2 page report on each paper as well as final report in which you write a more detailed discussion of the related work and surrounding scholarship on one of the papers.
Undergraduates are encourage to take CS114. Reports by students taking CS114 focus on the conceptual material in the papers and communicating an understanding of the basics of the topic area. Graduate students are encouraged to take CS214. Reports by students taking CS214 focus on explaining the ideas in the paper and their potential implications to the student's area of specialization.
The guest lectures are open to the entire Stanford community. Due to the depth of the technical material, we do not recommend the course to students who have not completed the CS core (CS111 and CS161) or have an equivalent engineering background. If you have questions about these preprequisites, please contact the course staff.
3/28 | Course Goals and (other reading: , ) |
3/30 | Lecture: (by ) , , , , , , , |
4/4 | Guest Lecture: , UC Berkeley |
4/6 | Lecture: (by ) , , , |
4/11 | Guest Lecture: , University of Vermont ( ) |
4/13 | Lecture: (by ) , , , |
4/18 | Guest Lecture: , Stanford University ( ) |
4/20 | Lecture: (by ) , , , |
4/25 | Guest Lecture: , UC Berkeley ( ) |
4/27 | Lecture: (by ) , , , , |
5/2 | Guest Lecture: , Stanford University ( ) |
5/4 | Lecture: (by ) , |
5/9 | Guest Lecture: , Harvard University ( ) |
5/11 | Lecture: (by ) , |
5/16 | Guest Lecture: , Northeastern University ( ) |
5/18 | Lecture: Paper (by ) |
5/23 | Guest Lecture: , Vanderbilt University ( ) |
5/25 | TBD |
5/30 | Memorial Day (no class) |
6/1 | Wrap-up |
Each student is required to write a 2-page (~1000 words) report on each paper. The report is due at 7PM on the Sunday before the guest lecture by the paper author. Your report for "Optimality of the Johnson-Lindenstrauss Lemma," for example, is due Sunday, April 3 at 7PM. Send your report as a PDF (not a link) to the staff mailing list. Your final report is due at 7PM on June 1st (the last day of classes).
Machine learning is a rapidly evolving field with research papers often serving as the foundation for discoveries and advancements. For anyone keen to delve into the theoretical and practical aspects of machine learning, the following ten research papers are essential reads. They cover foundational concepts, groundbreaking techniques, and key advancements in the field.
Table of Content
2. “imagenet classification with deep convolutional neural networks” by alex krizhevsky, ilya sutskever, and geoffrey e. hinton, 3. “playing atari with deep reinforcement learning” by volodymyr mnih et al., 4. “sequence to sequence learning with neural networks” by ilya sutskever, oriol vinyals, and quoc v. le, 5. “attention is all you need” by ashish vaswani et al., 6. “generative adversarial nets” by ian goodfellow et al., 7. “bert: pre-training of deep bidirectional transformers for language understanding” by jacob devlin et al., 8. “deep residual learning for image recognition” by kaiming he et al., 9. “a survey on deep learning in medical image analysis” by geert litjens et al., 10. “alphago: mastering the game of go with deep neural networks and tree search” by silver et al..
This article highlights 10 must-read machine learning research papers that have significantly contributed to the development and understanding of machine learning. Whether you’re a beginner or an experienced practitioner, these papers provide invaluable insights that will help you grasp the complexities of machine learning and its potential to transform industries.
Summary : Pedro Domingos provides a comprehensive overview of essential machine learning concepts and common pitfalls. This paper is a great starting point for understanding the broader landscape of machine learning.
Access: Read the Paper
Summary : Often referred to as the “AlexNet” paper, this work introduced a deep convolutional neural network that significantly improved image classification benchmarks, marking a turning point in computer vision.
Summary : This paper from DeepMind presents the use of deep Q-networks (DQN) to play Atari games . It was a seminal work in applying deep learning to reinforcement learning.
Summary : This paper introduced the sequence-to-sequence (seq2seq) learning framework , which has become fundamental for tasks such as machine translation and text summarization.
Summary : This paper introduces the Transformer model, which relies solely on attention mechanisms, discarding recurrent layers used in previous models. It has become the backbone of many modern NLP systems.
Summary : Ian Goodfellow and his colleagues introduced Generative Adversarial Networks (GANs) , a revolutionary framework for generating realistic data through adversarial training.
Summary : BERT (Bidirectional Encoder Representations from Transformers) introduced a new way of pre-training language models, significantly improving performance on various NLP benchmarks.
Summary : This paper introduces Residual Networks (ResNets), which utilize residual learning to train very deep neural networks effectively.
Summary : This survey provides a comprehensive review of deep learning techniques applied to medical image analysis, summarizing the state of the art in this specialized field.
Summary : This paper describes AlphaGo, the first AI to defeat a world champion in the game of Go, using a combination of deep neural networks and Monte Carlo tree search.
These ten research papers cover a broad spectrum of machine learning advancements, from foundational concepts to cutting-edge techniques. They provide valuable insights into the development and application of machine learning technologies, making them essential reads for anyone looking to deepen their understanding of the field. By exploring these papers, you can gain a comprehensive view of how machine learning has evolved and where it might be heading in the future.
What are large language models (llms) and why are they important.
Large Language Models (LLMs) are advanced AI systems designed to understand and generate human language. They are built using deep learning techniques, particularly transformer architectures. LLMs are important because they enable applications such as text generation, translation, and sentiment analysis, significantly advancing the field of natural language processing (NLP).
Pedro Domingos’ paper provides a broad overview of key machine learning concepts, common challenges, and practical advice. It’s an excellent resource for both beginners and experienced practitioners to understand the underlying principles of machine learning and avoid common pitfalls.
The “AlexNet” paper revolutionized image classification by demonstrating the effectiveness of deep convolutional neural networks. It significantly improved benchmark results on ImageNet and introduced techniques like dropout and ReLU activations, which are now standard in deep learning.
Similar reads.
Advanced topics in computer science: systems and machine learning.
In this graduate seminar, we plan to read and discuss two types of recent research papers at the intersection between systems and machine learning (ML): systems for ML and ML for systems. The first category includes papers about building efficient hardware and software for ML, including parallel, distributed, secure, privacy-preserving systems. The second category includes papers about how to apply ML in designing hardware and software systems, including new data structures and optimization methods.
arXiv's Accessibility Forum starts next month!
Help | Advanced Search
Title: using large language models to create ai personas for replication and prediction of media effects: an empirical test of 133 published experimental research findings.
Abstract: This report analyzes the potential for large language models (LLMs) to expedite accurate replication of published message effects studies. We tested LLM-powered participants (personas) by replicating 133 experimental findings from 14 papers containing 45 recent studies in the Journal of Marketing (January 2023-May 2024). We used a new software tool, Viewpoints AI ( this https URL ), that takes study designs, stimuli, and measures as input, automatically generates prompts for LLMs to act as a specified sample of unique personas, and collects their responses to produce a final output in the form of a complete dataset and statistical analysis. The underlying LLM used was Anthropic's Claude Sonnet 3.5. We generated 19,447 AI personas to replicate these studies with the exact same sample attributes, study designs, stimuli, and measures reported in the original human research. Our LLM replications successfully reproduced 76% of the original main effects (84 out of 111), demonstrating strong potential for AI-assisted replication of studies in which people respond to media stimuli. When including interaction effects, the overall replication rate was 68% (90 out of 133). The use of LLMs to replicate and accelerate marketing research on media effects is discussed with respect to the replication crisis in social science, potential solutions to generalizability problems in sampling subjects and experimental conditions, and the ability to rapidly test consumer responses to various media stimuli. We also address the limitations of this approach, particularly in replicating complex interaction effects in media response studies, and suggest areas for future research and improvement in AI-assisted experimental replication of media effects.
Comments: | 24 pages, 3 figures, 2 tables |
Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
Cite as: | [cs.CL] |
(or [cs.CL] for this version) | |
Focus to learn more arXiv-issued DOI via DataCite |
Access paper:.
Code, data and media associated with this article, recommenders and search tools.
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .
IMAGES
VIDEO
COMMENTS
Covers applications of computer science to the mathematical modeling of complex systems in the fields of science, engineering, and finance. ... Papers on all aspects of machine learning research (supervised, unsupervised, reinforcement learning, bandit problems, and so on) including also robustness, explanation, fairness, and methodology. cs.LG ...
Computer science is the study and development of the protocols required for automated processing and manipulation of data. This includes, for example, creating algorithms for efficiently searching ...
Explore the latest full-text research PDFs, articles, conference papers, preprints and more on COMPUTER SCIENCE. Find methods information, sources, references or conduct a literature review on ...
arXiv is a free distribution service and an open-access archive for nearly 2.4 million scholarly articles in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and systems science, and economics. Materials on this site are not peer-reviewed by arXiv.
Journal of Computer Science and Technology is an international platform publishing high quality, refereed papers in all aspects of computer science and technology. Sponsored by the Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), and China Computer Federation (CCF). Jointly published by ICT, CAS and Springer on a ...
Computer Science Review publishes research surveys and expository overviews of open problems in computer science. All articles are aimed at a general computer science audience seeking a full and expert overview of the latest developments across computer science research. Articles from other fields …. View full aims & scope.
zhefan-xu/onboard_detector • • 28 Feb 2023. Deploying autonomous robots in crowded indoor environments usually requires them to have accurate dynamic obstacle perception. Robotics. 84. 0.10 stars / hour. Paper. Code. Papers With Code highlights trending Computer Science research and the code to implement it.
Research institutions are under siege from cybercriminals and other digital assailants. ... A branch of computer science known as genetic programming has been given a boost with the application of ...
We publish many prestigious journals in Computer Science, including a number of fully open access journals. Our book and eBook portfolio comprises conference proceedings, book series, textbooks and major reference works from distinguished authors, such as recipients of the Turing Award. Well-known publications include: Lecture Notes in Computer ...
Covers all major branches of computer science, including emerging and multidisciplinary fields. Reflects international trends in research and development. Publishes original review articles, research papers, and special topic reports. Aims to keep researchers updated on the significant advancements in the field.
Computer Science is the study of computer systems and the impact that design, theory, and development have on society. The Computer Science Research Network on SSRN is an open access preprint server that provides a venue for authors to showcase their research papers in our digital library, speeding up the dissemination and providing the ...
Papers We Love (PWL) is a community built around reading, discussing and learning more about academic computer science papers. This repository serves as a directory of some of the best papers the community can find, bringing together documents scattered across the web. You can also visit the Papers We Love site for more info.
We also believe that highlighting excellent research will inspire others to enter the computing education field and make their own contributions.". The Top Ten Symposium Papers are: 1. " Identifying student misconceptions of programming " (2010) Lisa C. Kaczmarczyk, Elizabeth R. Petrick, University of California, San Diego; Philip East ...
This conceptual research paper is written to discuss the implementation of the A.D.A.B model in technology -based and technical subjects such as Computer Science, Engineering, Technical and so on ...
SN Computer Science publishes papers in the following categories: Original Research, as well as relevant hardware, and/or software architectures, Survey and Review Articles. All papers are evaluated on the basis of scientific content. Submissions are first screened for research and publication ethics prior to peer review.
The Journal of Computer Science (JCS) is dedicated to advancing computer science by publishing high-quality research and review articles that span both theoretical foundations and practical applications in information, computation, and computer systems. ... The best paper published by a young researcher will be selected by a journal committee ...
Part 1: Orientation to Small Group Systems Chapter 1: Small Groups as the Heart of Society Chapter 2: Groups as Structured Open Systems Part 2: Foundations of Small Group Communication Chapter 3: Communication Principles for Group Members... more. Download. by Gloria Galanes. Computer Science.
Computer Science Research Topics are as follows: Using machine learning to detect and prevent cyber attacks. Developing algorithms for optimized resource allocation in cloud computing. Investigating the use of blockchain technology for secure and decentralized data storage. Developing intelligent chatbots for customer service.
This section offers a well-organized and extensive list of 1000 computer science thesis topics, designed to illuminate diverse pathways for academic inquiry and innovation. Whether your interest lies in the emerging trends of artificial intelligence or the practical applications of web development, this assortment spans 25 critical areas of ...
An e-print service which presents papers in physics, mathematics, nonlinear science, computer science, quantitative biology, quantitative finance, and statistics. arXiv.org is a fully automated electronic archive and distribution server for research papers which functions as a means of communicating ongoing research information in these subject ...
Computer Science. Computer science deals with the theory and practice of algorithms, from idealized mathematical procedures to the computer systems deployed by major tech companies to answer billions of user requests per day. Primary subareas of this field include: theory, which uses rigorous math to test algorithms' applicability to certain ...
Provides searchable, full text access to new developments in computer science and information technology research and teaching. Original research results reported in proceedings and post-proceedings remains the core of LNCS. Dates of coverage: 1997-2017
Human-centered Cybersecurity Research — Anthropological Findings from Two Longitudinal Studies, Anwesh Tuladhar. PDF. Learning State-Dependent Sensor Measurement Models To Improve Robot Localization Accuracy, Troi André Williams. PDF. Human-centric Cybersecurity Research: From Trapping the Bad Guys to Helping the Good Ones, Armin Ziaie Tabari
Selected Readings of CS Research examines 8 selected papers by leading scholars in computer science and electrical engineering. The papers cover a wide range of subfields within CS and EE. Students taking this course will learn about a broad view of research fields in EE and CS, including what kinds of problems different fields tackle as well ...
The research also explores teachers' and students' ability to discern the source of these explanations. ... an AI model, in comparison to those created by human teachers. To achieve this, explanations of fundamental concepts in computer science—sequence, selection, and iteration—crafted by both human teachers and GPT-3.5 were presented to ...
A Computer Science portal for geeks. It contains well written, well thought and well explained computer science and programming articles, quizzes and practice/competitive programming/company interview Questions. ... Machine learning is a rapidly evolving field with research papers often serving as the foundation for discoveries and advancements ...
In this graduate seminar, we plan to read and discuss two types of recent research papers at the intersection between systems and machine learning (ML): systems for ML and ML for systems. The first category includes papers about building efficient hardware and software for ML, including parallel, distributed, secure, privacy-preserving systems.
This report analyzes the potential for large language models (LLMs) to expedite accurate replication of published message effects studies. We tested LLM-powered participants (personas) by replicating 133 experimental findings from 14 papers containing 45 recent studies in the Journal of Marketing (January 2023-May 2024). We used a new software tool, Viewpoints AI (https://viewpoints.ai/), that ...
The research presented here proposes a completely innovative interpretation of how this colossal monument was built. ... (iii) the depth of the foundations. Our results show that Menga is a unique example of creative genius and early science among Neolithic societies. It was designed as a completely original engineering project, for which we ...
Understanding this, the Research.com team has meticulously crafted the "2024 Best Computer Science Degree Programs Ranking in America" to assist prospective students in making informed choices. Our commitment to quality, credibility, and accuracy is reflected in the comprehensive data analysis we conducted, utilizing reputable sources to ...