Artificial Intelligence (AI): Literacy Toolbox

• Algorithm: In computing, an algorithm is a precise list of operations that a Turing machine could do. For the purpose of computing, algorithms are written in pseudocode, flow charts, or programming languages.  https://simple.m.wikipedia.org/wiki/Algorithm
• Artificial Intelligence: The theory and development of computer systems able to perform tasks that usually require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages. https://www.lexico.com/en/definition/artificial%20intelligence
• Deep Learning: In practical terms, deep learning is just a subset of machine learning. In fact, deep learning technology is machine learning and functions in a similar way (hence why the terms are sometimes loosely interchanged). However, its capabilities are different. While basic machine learning models do become progressively better at whatever their function is, they still need some guidance. If an AI algorithm returns an inaccurate prediction, then an engineer has to step in and make adjustments. With a deep learning model, an algorithm can determine on its own if a prediction is accurate or not through its own neural network. https://www.zendesk.com/blog/machine-learning-and-deep-learning/
• Imitation Learning: Generally, imitation learning is useful when it is easier for an expert to demonstrate the desired behavior rather than to specify a reward function that would generate the same behavior or to directly learn the policy. The main component of IL is the environment, which is essentially a Markov Decision Process (MDP).  https://smartlabai.medium.com/a-brief-overview-of-imitation-learning-8a8a75c44a9c
• Machine Learning: Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it... learn for themselves.  https://expertsystem.com/machine-learning-definition/
• Neural Network in AI: A neural network is a method in artificial intelligence that teaches computers to process data in a way that is inspired by the human brain. It is a machine learning process, called deep learning, that uses interconnected nodes or neurons in a layered structure that resembles the human brain. It creates an adaptive system that computers use to learn from their mistakes and improve continuously. Thus, artificial neural networks attempt to solve complicated problems, like summarizing documents or recognizing faces, with greater accuracy.  https://aws.amazon.com/what-is/neural-network/
• Reinforcement Learning: In this kind of machine learning, AI agents are attempting to find the optimal way to accomplish a particular goal, or improve performance on a specific task. As the agent takes action that goes toward the goal, it receives a reward. The overall aim: predict the best next step to take to earn the biggest final reward. https://blogs.nvidia.com/blog/2018/08/02/supervised-unsupervised-learning/
• Supervised and Unsupervised Learning: In a supervised learning model, the algorithm learns on a labeled dataset, providing an answer key that the algorithm can use to evaluate its accuracy on training data. An unsupervised model, in contrast, provides unlabeled data that the algorithm tries to make sense of by extracting features and patterns on its own. https://blogs.nvidia.com/blog/2018/08/02/supervised-unsupervised-learning/

What are the Risks of Using AI & Generative Chat Apps?

AI models sometimes produce incorrect, biased, or outdated information. Verify the accuracy of AI-generated content using reliable sources before including it in your work.

Additionally, there may be legal or ethical issues to consider when using AI. Works created by non-humans are not eligible for copyright protection under Australian law. If you intend to publish work incorporating AI-generated content, check the publisher guidelines about what is allowed.

When interacting with AI models, you should be cautious about supplying sensitive information, including personal, confidential, or proprietary information or data.

Artificial intelligence can be a helpful tool in the information literacy toolbox for topic brainstorming, writing refinement, and cross-disciplinary perspectives. Generative AI could also give first-generation college students a chance to compete on an equal footing in culturally biased environments, as they are often more resourceful and creative in their approach to academics and campus life. However, there are known issues with ChatGPT’s accuracy and reliability. It can appear to researchers as an authority on any given subject by providing citations to sources that do not exist or are not relevant to the topic being discussed. This can make it difficult for researchers to find accurate information and can lead to them making incorrect conclusions. Unfortunately, ChatGPT, like a large percentage of Artificial Intelligence, also has well-documented issues of bias and misinformation. This is because AI systems are trained on data that is often biased, and this bias can be reflected in the output of the system. For example, if an AI system is trained on a dataset of news articles that are mostly from one political perspective, the system may be more likely to generate text that reflects that perspective. Additionally, AI systems can be easily manipulated to generate false or misleading information. For example, an attacker could create a fake news article and then use an AI system to generate text that supports the article. This text could then be spread online, making it difficult to distinguish between real and fake news. In some cases, an overcorrection to combat bias has led to these communities being left out of the conversation completely. It is important to be aware of the potential for bias and misinformation when using AI systems and to take steps to mitigate these risks. Librarians at FIU are hoping to develop tools to promote AI literacy and the evaluation of generative AI.