IP#2 - Artificial Intelligence

Question #1 - Who were the following people, and how did/does each contribute to the development of artificial intelligence? How did/does each think “intelligence” could be identified?

Alan Matheson Turing  (1912-1954)

My Response: He is the father of computer science and artificial intelligence (AI). He developed the Universal Turing Machine, which was the basis for the first computer. He also created the Turing test for AI which is still used today. According to his test, a machine can respond in a way that humans cannot recognize to be different from another human, thus indicating a possession of “intelligence”.

 

ChatGPT Response (Edited): Alan Turing was a British mathematician, computer scientist and codebreaker who made major contributions to the development of computer science and artificial intelligence. After the war, he developed the idea of a machine, now known as the Universal Turing machine. He also proposed the concept of the "Turing Test" as a way to determine a machine's ability to exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human.


John McCarthy (1927 - 2011)

My Response: He coined the term Artificial Intelligence (AI) and created the computer programming language LISP which aided in much of the early research done in AI. To him Intelligence is the computational part of the ability to achieve goals in the world (Sutton, 2020).

ChatGPT Response (Edited): John McCarthy is considered one of the founders of the field of artificial intelligence and coined the term “artificial intelligence”. He developed LISP programming language, which remains one of the most widely used programming languages for AI and machine learning applications. McCarthy believed that intelligence could be identified by the ability of a system to perform tasks that would normally require human intelligence. He also believed that intelligence could be simulated through the use of mathematical algorithms and computer programs.

Herbert A. Simon (1916 - 2001)

My Response: He contributed to AI through the development of the General Problem Solver which spoke to his theory of human problem solving in a simulation program. Simon believed that intelligence was the ability to solve problems efficiently and effectively and that intelligence is not a single entity, but rather a collection of cognitive processes.

ChatGPT Response (Edited): Herbert A. Simon is considered to be one of the pioneers of artificial intelligence and made significant contributions to the field. Simon's work focused on developing mathematical models of human problem-solving and decision-making processes "bounded rationality". Simon believed that intelligence could be identified by the ability to solve problems efficiently and effectively. He argued that intelligence is not a single entity, but rather a collection of cognitive processes, such as perception, learning, and memory, that are used to process information and make decisions. He also believed that intelligence can be modeled and emulated by computers, and his work laid the foundations for the development of artificial intelligence as a field of study.

Marvin Minsky (1927 - 2016)

My Response: He believed the human brain was a type of machine that could be recreated by a computer (BBC News, 2016). He greatly influenced early work on learning machines. He believed intelligence to be our name for whatever processes we don't yet understand (Shulz, 2023).

ChatGPT Response (Edited): Marvin Minsky was a pioneer in the field of artificial intelligence. Minsky's contributions to the development of AI include his work on symbolic reasoning, natural language processing, and neural networks. Minsky believed that intelligence could be identified by a machine's ability to perform tasks that would typically require human intelligence, such as understanding natural language, recognizing objects, and solving problems.

Timnit Gebru (1982)

My Response: She is widely recognized for her expertise in AI and her advocacy for diversity in technology and she cofounded Black in AI. Her views on technology really focus on AI being fair and just and that take human experiences and perspectives into account.

ChatGPT Response (Edited): Timnit Gebru is known for her work on issues of ethics and fairness in AI, as well as her contribution to the field of computer vision. She is developing methods to reduce bias in AI systems and improve the accuracy of algorithms in recognizing and processing images. Gebru's views on "intelligence" are rooted in her belief that AI should be developed in a way that is fair and just, taking into account the impact it will have on society.

Question #2 - How do “machine (programming) languages” differ from human (natural) ones?

My Response: Language can be defined as a system of spoken, manual, or written symbols that human beings use to express themselves, their identity, imagination, and emotions. Programming languages revolve around the same principle of communication. They were created by humans as a system of symbols and rules used to communicate a set of instructions to a machine/computer. Although a lot simpler in their nature (Harris, 2018). It is really interesting to dive into language in this way as a language learner and teacher. Human languages differ greatly based on alphabet, accents, vocabulary, slang, etc. People who are learning a different language to immerse themselves in a culture would find it much more difficult then someone in a programming language field who is learning a new language. Although we may have rules when teaching a language it is very fluent and they are always being broken or, as I say a lot when teaching French that is an exception. Programming however is much more black and white (or 1 & 0 if you will). It is fairly universal and can be understood by people who speak many different human languages, and it has rules that must be followed there is no room for exceptions. 

ChatGPT Response: Machine languages are used to program computers and are comprised of binary code that computers can understand and execute. They are difficult for humans to read and write. On the other hand, natural languages are used by humans to communicate with one another and are more easily understood by humans. They are less precise and more ambiguous than machine languages, which can make them difficult for computers to interpret accurately. Additionally, natural languages have a broader context and cultural context, whereas machine languages only have a defined syntax and set of rules for execution.

Question #3 - How does “machine (artificial) intelligence” differ from the human version?

My response: Human Intelligence aims to adapt to new environments by utilizing a combination of different cognitive processes, Artificial Intelligence aims to build machines that can mimic human behavior and perform human-like actions. The human brain is analogous, but machines are digital (Vadapalli, 2022). Machine Intelligence is trying to replicate human behaviour and do tasks just like humans would, however, humans aim to adapt to their surroundings using different thought processes. For example, if we walk into a grocery store in a new country we must learn and adapt to the names for their foods, how to navigate the store, what brands they may have, and even how to communicate with those that work there. However, for machines they would have to take information about that store and try to understand how to navigate this new environment in the same way we would. Machine intelligence relies on it creating its own algorithm whereas humans develop and change our own unique algorithm for dealing with the experiences life brings to us.

ChatGPT Response: Artificial intelligence (AI) is a branch of computer science that aims to create systems that can perform tasks that typically require human intelligence, such as recognizing speech, making decisions, and translating languages. AI systems are designed to perform these tasks based on algorithms, large amounts of data, and powerful computer processors, whereas human intelligence is the result of complex interactions between our genes, environment, and experience. AI systems are limited by the data they have been trained on and the algorithms used, whereas human intelligence is more flexible, context-dependent, and able to learn from experience. In short, AI is a limited form of intelligence that is designed to perform specific tasks, whereas human intelligence is more general and adaptive.

Question #4 - How does “machine learning” differ from human learning?

My response: Whether its Human Learning or Machine Learning — both involve “observations” about a thing or a process or phenomenon. And then, identifying patterns about these observations. The expression of this pattern is the model that has been learned. Humans attain their knowledge through either direct or shared experiences, but machines acquire their knowledge through shared forms of past data. I find it really interesting however, that despite companies like IBM who have built simulators with 7x as many neurons as we have in our brains right now (thus indicating machines have more learning power than a human brain), machines still aren’t considered to be able to function at the same capacity as the human brain (Kaplan, 2022). This is because machines cannot consider other criteria nor reflect upon the, (no feeling or perception means they are inflexible and can’t change course) unlike humans.

 

ChatGPT Response: Machine learning differs from human learning in several ways:

Speed: Machines can learn much faster than humans, processing large amounts of data in seconds or minutes.

Consistency: Machines do not get tired, make mistakes or have biases, ensuring consistent and accurate results.

Data-Driven: Machine learning algorithms are trained on data and make predictions based on patterns found in that data, while human learning is driven by experience, intuition, and prior knowledge.

Lack of creativity: Machines lack the ability to think creatively and come up with new ideas, unlike humans.

Limited understanding: Machines lack a deep understanding of the context and meaning of the data they work with, whereas humans can contextualize and understand the world around them.

Question #5 - How do YOUR answers to these questions differ from what a machine could generate?

I found looking back and analyzing the ChatGPT and my responses was a very interesting assignment. I firstly found ChatGPT to be eerily interesting to discover through this week’s assignment and readings. I have never heard of this program and find it to be both interesting as well as daunting as a teacher. Although I may not face students using this in my classrooms (elementary) I can see how something like this can be a way for students to get by without really having to do the work (great knowledge to now possess as an educator).

 

When really observing my responses and the ChatGPT:

1.      The first thing that really struck me was its lack of recognition. The ChatGPT doesn’t reference where it is formulating this information from or who has provided the information. This is something I also see as a downfall to the program. It doesn’t give recognition where it is due.

2.     ChatGPT does not give examples or personal experience to the responses it gives. When I am responding, if it is relevant or helpful to the information being shared, I give personal accounts or examples of how this information is relevant to me and my experiences.  I believe this is a great example of how we see the downfall machines possess in being able to provide personal connection and not just fact.  

3.     Vocabulary and sentence structures with ChatGPT differ from my own rhetoric. I found this to be a huge difference between my answers and the Chat. I would never use certain vocabulary or feel the need to add all the extra details to my own writing when responding to these types of questions.

 

There are so many differences that can be found between my own production/responses and those of ChatGPT which, as you stated, we could spend weeks exploring through different questions. I do intend on continuing to explore this platform as a means to aid when I struggle to understand what a question may be asking or when I am looking for a direction to take in a subject matter, or even when I want to see a commentary that will be untouched by my own bias.

References

Question #1 

A&E Networks Television. (2020). Alan Turing. Biography.com. Retrieved February 5, 2023, from https://www.biography.com/scientists/alan-turing

BBC. (2016, January 26). Ai pioneer Marvin Minsky dies aged 88. BBC News. Retrieved February 5, 2023, from https://www.bbc.com/news/technology-35409119

Encyclopædia Britannica, inc. (n.d.). John McCarthy. Encyclopædia Britannica. Retrieved February 5, 2023, from https://www.britannica.com/biography/John-McCarthy

Hao, K. (2022, January 10). We read the paper that forced Timnit Gebru out of google. here's what it says. MIT Technology Review. Retrieved February 5, 2023, from https://www.technologyreview.com/2020/12/04/1013294/google-ai-ethics-research-paper-forced-out-timnit-gebru

Jacobson, R. (2014, November 28). 8 things you didn't know about Alan Turing. PBS. Retrieved February 5, 2023, from https://www.pbs.org/newshour/science/8-things-didnt-know-alan-turing#:~:text=Turing's%20most%20notable%20work%20today,which%20is%20still%20used%20today.

Last Updated November 30th, 2018 07:04 pm. (2018, November 30). General problem solver (A. newell & H. simon). InstructionalDesign.org. Retrieved February 5, 2023, from https://www.instructionaldesign.org/theories/general-problem-solver/

Schulz, E. M. (2023). Philosophy dictionary of arguments. Marvin Minsky on Intelligence - Dictionary of Arguments. Retrieved February 5, 2023, from https://philosophy-science-humanities-controversies.com/listview-details.php?id=452246&a=t&first_name=Marvin&author=Minsky&concept=Intelligence#:~:text=Minsky%20I%2071,we%20don't%20yet%20understand.

Sutton, R. S. (2020). John McCarthy’s Definition of intelligence - incompleteideas.net. Journal of Artificial General Intelligence. Retrieved February 5, 2023, from http://incompleteideas.net/papers/Sutton-JAGI-2020.pdf

The economics of altruism. https://www.ubs.com/microsites/nobel/en/laureates/herbert-simon.html. (n.d.). Retrieved February 5, 2023, from https://www.ubs.com/microsites/nobel-perspectives/en/laureates/herbert-simon.html

Wikimedia Foundation. (2023, January 22). Timnit Gebru. Wikipedia. Retrieved February 5, 2023, from https://en.wikipedia.org/wiki/Timnit_Gebru#:~:text=Timnit%20Gebru%20(Amharic%3A%20%E1%89%B5%E1%88%9D%E1%8A%92%E1%89%B5%20%E1%8C%88%E1%89%A5%E1%88%A9,in%20artificial%20intelligence%20(AI).


Question #2

Harris, A. (2018, November 1). Human languages vs. programming languages. Medium. Retrieved February 5, 2023, from https://medium.com/@anaharris/human-languages-vs-programming-languages-c89410f13252

Petterson, E. (2021, December 22). Are programming languages actually languages? Lucidchart. Retrieved February 5, 2023, from https://www.lucidchart.com/techblog/2021/12/21/are-programming-languages-actually-languages/#:~:text=Differences%20between%20programming%20languages%20and,of%20expression%20of%20human%20languages. 


Question #3 

Chollet, F. (2019, November 25). On the measure of Intelligence. arXiv.org. Retrieved February 5, 2023, from https://arxiv.org/abs/1911.01547 

Gandhi, S. (2018, June 9). Artificial Intelligence - Demystified. Medium. Retrieved February 5, 2023, from https://towardsdatascience.com/artificial-intelligence-demystified-a456328e193f

Nielsen, L. K. B. (2016, December). Microsoft. Microsoft Support. Retrieved February 5, 2023, from https://support.microsoft.com/en-us/windows/find-my-downloads-in-windows-10-de903ee9-7d37-256b-9145-f0f016c5aed8 

Vadapalli, P. (2022, October 3). Ai Vs Human Intelligence: Difference between AI & Human Intelligence. upGrad blog. Retrieved February 5, 2023, from https://www.upgrad.com/blog/ai-vs-human-intelligence/#:~:text=While%20Human%20Intelligence%20aims%20to,analogous%2C%20but%20machines%20are%20digital.


Question #4

Goel, G. (2020, July 7). Human learning vs machine learning. Medium. Retrieved February 5, 2023, from https://towardsdatascience.com/human-learning-vs-machine-learning-dfa8fe421560

IBM. (2022). What is machine learning? IBM. Retrieved February 5, 2023, from https://www.ibm.com/topics/machine-learning#:~:text=Machine%20learning%20is%20a%20branch,learn%2C%20gradually%20improving%20its%20accuracy.

J. P. S. (2020, April 2). Human learning and machine learning - how they differ ? Data Science Central. Retrieved February 5, 2023, from https://www.datasciencecentral.com/human-learning-and-machine-learning-how-they-differ/#:~:text=Let%20us%20examine%20the%20difference,the%20form%20of%20past%20data.

Kaplan, D. (2022, December 30). The battle of our future: Machine learning vs. human learning " EML. EML. Retrieved February 5, 2023, from https://enjoymachinelearning.com/blog/machine-learning-vs-human-learning/ 


Question #5