Artificial Intelligence (A.I.), a term introduced by the esteemed Stanford Professor John McCarthy in 1955, was originally described as "the science and engineering of making intelligent machines." Initially, AI research centered on programming machines to demonstrate certain behaviors, like playing games. However, the current focus is on crafting machines with the capacity to learn, resembling aspects of human learning processes.
Andresen, S. L. (2002). John McCarthy: father of AI. IEEE Intelligent Systems, 17(5), 84-85
Artificial intelligence (A.I.) refers to the capacity of computers or other machines to perform tasks that typically require human intelligence such as reasoning, problem-solving, and decision-making. AI systems use algorithms and computational techniques to process large volumes of data, extract patterns, and make predictions or decisions based on those patterns.
A short history of artificial intelligence work at Stanford University from Stanford University School of Engineering
An interview with John McCarthy from the Simons Foundation
This search box will allow you to search OCC Discovery. It includes physical and online books, videos, and articles from most library databases.
Artificial intelligence (AI) refers to a broad branch of computer science focused on creating systems capable of simulating the human capacity for learning and dynamic, real-time problem-solving based on firsthand observations, inferences, and interactions with their surroundings. Most functional AI in use as of the early 2020s is built on massive, human-generated data sets and algorithms, complex sets of instructions and calculations computer systems use to carry out procedures or complete tasks. OCC LIbrary Database.
Conducting Library research for the topic of Artificial Intelligence (AI) encompasses a rapidly changing field, so let's prompt ChatGPT for what is AI.
Response (OpenAI, 2024):
Artificial Intelligence (AI) refers to the simulation of human intelligence in machines programmed to think and learn like humans. This includes tasks such as problem-solving, understanding natural language, recognizing patterns, and making decisions. AI can be classified into two main types:
AI systems often use techniques from machine learning, where they improve their performance through experience, and deep learning, which involves neural networks processing large amounts of data.
Here are some key terms to understand in the context of A.I.:
Machine Learning (ML): A subset of AI focused on algorithms that allow computers to learn from and make predictions based on data.
Deep Learning: A specialized form of machine learning using neural networks with many layers, effective for complex tasks like image and speech recognition.
Neural Networks: A framework inspired by the human brain, used in deep learning to process data and recognize patterns.
Natural Language Processing (NLP): The branch of AI that deals with the interaction between computers and human language, enabling machines to understand, interpret, and respond to text or speech.
Supervised Learning: A type of machine learning where the model is trained on labeled data, meaning the input comes with the correct output.
Unsupervised Learning: A type of machine learning that deals with unlabeled data, aiming to find hidden patterns or intrinsic structures in the data.
Reinforcement Learning: A learning paradigm where an agent learns to make decisions by receiving rewards or penalties based on its actions in an environment.
Computer Vision: The field of AI focused on enabling machines to interpret and understand visual information from the world.
Bias: Refers to systematic errors in AI predictions or decisions that arise from the data used to train models, often reflecting societal biases.
Automation: The use of AI to perform tasks without human intervention, increasing efficiency and reducing the need for manual labor.
Generative AI: AI systems that can create new content, such as images, music, or text, based on learned patterns from existing data.
Transfer Learning: A technique where a model developed for one task is reused for a different but related task, reducing the need for large amounts of new data.
Overfitting: A modeling error that occurs when a model learns the training data too well, including its noise and outliers, which negatively impacts its performance on new data.
Underfitting: The opposite of overfitting, where a model is too simple to capture the underlying trends in the data, resulting in poor performance.
Feature Engineering: The process of selecting, modifying, or creating new input variables (features) to improve model performance.
Data Augmentation: Techniques used to increase the diversity of training data without actually collecting new data, often used in image processing.
Explainable AI (XAI): Approaches and methods that make the decision-making processes of AI systems more transparent and understandable to humans.
Robotics: The branch of technology that deals with the design, construction, and operation of robots, often incorporating AI for automation and decision-making.
Edge Computing: A computing paradigm that processes data near the source of data generation, which can enhance the efficiency and speed of AI applications.
Chatbot: An AI application designed to simulate conversation with human users, often used for customer service or information retrieval.
Understanding these terms provides a solid foundation for exploring AI concepts further!
Books & eBooks can provide a broad overview of a topic or in-depth information. You can search for books by author, title, subject, or keyword. Use the following terms as Subject heading and Keywords search strategies for books & ebooks on your topic:
Ebsco's eBooks provides electronic full-text copies of over 19,000 published print materials, such as reference books, scholarly monographs, fiction, and nonfiction books.
This set of eBooks covers many topics, but is particularly strong in literature, religion and history. Many books in the Bloom's series are available, as well the texts of sacred works. This site also has many career guides.
Springer's eBooks provides electronic full-text copies of over 12,000 published print materials, such as reference and scholarly books. These books are available to download in PDF format, with no DRM.
This site provides electronic full-text copies of several multi-volume reference and scholarly books. Titles cover history, business, literature and more.
A collection of reference books from Oxford publishing.
The Salem Press site allows you to access online certain reference books from the library's collection. Some of the titles included are Magill's Medical Guide, The Encyclopedia of American Immigration, Great Events from History, Careers in..., Critical Survey..., and The Encyclopedia of Global Warming.
1. Enter your keywords
2. Select "Library Catalog" from the dropdown
3. When the results appear, click on "Resource Type" and select Books
4. Look through the results of print and electronic books
Article databases provide you with 24-7 access to magazine, journal and newspaper articles. To help you identify the most appropriate database for your research topic:
Depending on the database you are using, articles may be displayed in different formats:
Most databases at OCC will default to show you only full-text results. You can often change this option, if you wish.
Periodicals are publications which are issued at regular intervals, such as journals, magazines, and newspapers. It can be difficult to distinguish between the various types of periodicals when they are in electronic format. Luckily, many databases allow researchers to search or sort results by publication type.
To help you identify different periodicals, refer to the Types of Periodicals guide.
On the search interface of the database, look for options to limit your results by scholarly journal, peer-reviewed journals, industry publications, or similar, as needed.
You can now search the OCC Library's journal content by DOI. Simply copy and paste your article's DOI in the box and you'll see if the library has it and how you can access it. There are some resources that are not available here, so, when in doubt, contact your friendly OCC librarians.
A search string is a combination of keywords, boolean operators, and truncation symbols you enter into the search box of a library database or search engine. Review our Search Strategies for tips.
►Boolean operators are connector words, such as AND, OR, and NOT, that are used to combine or exclude words in a search string for more focused results.
►Truncation or wildcard symbols allow you to look for variations of words. They often broaden your search results. For example, searching on sport* would bring up variations such as sport, sports, sporting, sporty, etc.
Note: Wildcards vary across database platforms. Common wildcards symbols are the question mark ? and hash # symbols. Consult the database’s “help” or “search tips” pages for details.
Artificial Intelligence (AI) Ethics: Ethics of AI and Ethical AI (PDF)
Artificial Intelligence and Life in 2030: The One Hundred Year Study on Artificial Intelligence
The Institute for Ethical AI in Education
An overview of current trends in regulating AI in different regions and discusses the key ethical issues to establishing fair and inclusive regulatory systems at the global level - The United Nations Educational, Scientific and Cultural Organization (UNESCO)
Stanford Encyclopedia of Philosophy
The Alan Turing Institute
AI changes so quickly that it can be difficult to keep up with the latest innovations. Furthermore, this rate of rapid change makes it challenging to find sources that balance the opportunities and possibilities of utilizing AI with the threats made possible by misuse of the technology. The following suggested resources are provided as starting points for researching various aspects of AI.
Resource page with an overview of current career opportunities and how the field is expanding to new industry sectors.
This site offers some useful background information, including history, potential uses, and trends. Note: this is a private company, not a research institute.
Podcast with interviews and stories exploring AI across the world
An organization that combines art and research to highlight the social implications and harms of AI.
Produces diagnosis and actionable policy research on AI.
The Daily-AI workshop, designed by MIT educators and experienced facilitators, features hands-on and computer-based activities on AI concepts, ethical issues in AI, creative expression using AI, and how AI relates to your future.
To help you identify websites, see if there is a Subject Guide for your research topic.
If you cannot find a relevant subject guide, remember to evaluate the websites you find before you use them in your research assignments.
Google Scholar provides an easy way to search for scholarly literature across many disciplines and resources. However, be aware that many of the articles you find will be behind a paywall. The best place to find this content is through your library's databases.
According to the Guidelines for Artificial Intelligence (AI)-Generated Text (based on IEEE Author Center Submission Guidelines),
The use of content generated by artificial intelligence (AI) (including but not limited to text, figures, images, and code) shall be disclosed in an acknowledgments section. The AI system used shall be identified, and specific sections of the document that use AI-generated content shall be identified and accompanied by a brief explanation regarding the level at which the AI system was used to generate the content. The use of AI systems for editing and grammar enhancement should be disclosed as noted above.
IEEE has not published an official guideline on citing AI-generated content yet. The IEEE Author Center recommends consulting the Chicago Manual of Style for guidance for any usage not included in the IEEE Editorial Style Manual. The Chicago Manual of Style has recommendations on how to cite AI-generated content.
APA format: Author. (Date).Title (Month Day version) [Additional Descriptions ]. Source
Author: The author of the model.
Date: The year of the version.
Title: The name of the model. The version number is included after the title in parentheses.
Bracketed text: References for additional descriptions
Source: When the publisher and author names are identical, omit the publisher name in the source element of the reference and proceed directly to the URL.
APA reference entry: OpenAI. (2023). ChatGPT (Feb 13 version) [Large language model]. https://chat.openai.com
APA in-text citation: (OpenAI, 2023)
Examples:
Example 1 from APA Guideline
When prompted with “Is the left brain right brain divide real or a metaphor?” the ChatGPT-generated text indicated that although the two brain hemispheres are somewhat specialized, “the notation that people can be characterized as ‘left-brained’ or ‘right-brained’ is considered to be an oversimplification and a popular myth” (OpenAI, 2023).
Reference
OpenAI. (2023). ChatGPT (Mar 14 version) [Large language model]. https://chat.openai.com/chat
Example 2 from APA Guideline
When given a follow-up prompt of “What is a more accurate representation?” the ChatGPT-generated text indicated that “different brain regions work together to support various cognitive processes” and “the functional specialization of different regions can change in response to experience and environmental factors” (OpenAI, 2023; see Appendix A for the full transcript).
Reference
OpenAI. (2023). ChatGPT (Mar 14 version) [Large language model]. https://chat.openai.com/chat
APA views quotes from a ChatGPT chat session as akin to sharing an algorithm’s output, and recommend crediting the author of the algorithm with a reference list entry and the corresponding in-text citation.
In-text citation example (from APA style blog): When prompted with “Is the left brain right brain divide real or a metaphor?” the ChatGPT-generated text indicated that although the two brain hemispheres are somewhat specialized, “the notation that people can be characterized as ‘left-brained’ or ‘right-brained’ is considered to be an oversimplification and a popular myth” (OpenAI, 2023).
OpenAI. (2023). ChatGPT (GPT-4) [Large language model]. https://chat.openai.com/chat
Please note (as per APA style blog): "The format for the version number in ChatGPT references includes the date because that is how OpenAI is labeling the versions. Different large language models or software might use different version numbering; use the version number in the format the author or publisher provides, which may be a numbering system (e.g., Version 2.0) or other methods."
Examples:
MLA format: “Text of prompt” prompt. ChatGPT, Day Month version, OpenAI, Day Month Year, chat.openai.com.
MLA Works Cited entry: “Explain antibiotics” prompt. ChatGPT, 13 Feb. version, OpenAI, 16 Feb. 2023, chat.openai.com.
MLA in-text citation: ("Explain antibiotics")
The Modern Language Association provides detailed guidance on citing generative AI according to their template.
Recommendations on how to cite AI-generated content
Example:
Chicago style recommends citing ChatGPT in a Chicago footnote
1. Text generated by ChatGPT, March 31, 2023, OpenAI, https://chat.openai.com.
The following two articles from the Chicago Style Q&A may be helpful to review:
University of Chicago Press generally recommends acknowledging the use of an AI tool in your text, but gives the following examples as format citations (examples drawn from "Citation, Documentation of Sources" on Chicago Style Q&A blog) :
1 Text generated by ChatGPT, OpenAI, March 7, 2023, https://chat.openai.com/
If the prompt hasn't been included in the text, it can be included in the note:
1 ChatGPT, response to "Explain how to make pizza dough from common household ingredients," OpenAI, March 7, 2023, https://chat.openai.com/
Any information not included in the text is placed in the parenthetical reference. Example:
Chat with a librarian by clicking on the speech bubble below anytime the library is open.
Stop by the Reference Desk to talk with a librarian.
Schedule a research appointment with a librarian.
Email your question to a librarian
Check out the OCC Library Frequently Asked Questions!
Use the same login that you use for MyOCC, Canvas, and your OCC email to login to the library's online resources.
If you have trouble logging in, please email us, use the chat button below, or call us at 714-432-0202 when the library is open.
OCC's Writing & Humanities Center can help you with your writing! They offer appointments to students seeking assistance writing their papers. Learn more through their website.
