Fairness AI materials

 

Fairness AI materials

https://medium.com/@docintangible/racist-data-destruction-113e3eff54a8

knowledge graph neural network and transformer

 for instrusion detection, knowledge graph model can train on intrusion data that are often much smaller than normal data. 

for transformer models, we need large amount of intrusion data which is unlikely. 

ECSI, student loans

 

ECSI stands for **Educational Computer Systems, Inc.** ¹. It is a company approved by the government to service federal Perkins student loans. It manages the loans, including collecting and tracking payments, but doesn’t own them. The company is sometimes referred to as Heartland ECSI ³.

Source: Conversation with Bing, 5/23/2023

(1) ECSI. https://home.ecsi.net/.

(2) ECSI Customer Service: What It Can Do and How to Contact. https://www.nerdwallet.com/article/loans/student-loans/ecsi-customer-service-what-it-can-do-and-how-to-contact.

(3) ECSI. http://heartland.ecsi.net/.

(4) ECSI Student Loan Review: What to Know About This Servicer - LendingTree. https://www.lendingtree.com/student/ecsi-student-loans-review/.

(5) ECSI Student Loan Servicing | Student Debt Warriors. https://studentdebtwarriors.com/ecsi-student-loan-servicing/.

UTC Travel card can be used for local events

 

I have checked with our AP/Travel staff and have learned it IS allowable to use your travel card for meals/refreshments for local events. You’ll submit in Concur and itemized receipts are required. If it is for fewer than 15 people, a list of participants will be required. Tip should not exceed 20%. Please let me know if you have any additional questions.

UTC CSE JUMP program

 

 

XYZ is a current Computer Science Data Science major in her last few semesters. She is thinking about going into grad school after completing her degree and would like to take advantage of the JUMP program. However, I am getting familiar with the approved courses. 

 

What courses are part of the Jump program at UTC?

There are three courses that have been approved to be part of the JUMP program. Students admitted to JUMP could take one, two, or all three of the following:

CPSC 5100 (in place of CPSC 4100)

CPSC 5590 (in place of CPSC 4550)

CPSC 5700 (in place of CPEN 4700)

Students in the Data Science concentration already take 4100 and 4700, so those would have direct substitutions as outlined above. For students (such as Data Science) not required to take CPSC 4550, if they were to take CPSC 5590 they could count it as an upper-level elective, just as if they had chosen 4550 as an elective.

Fall 2023 PhD application

To apply for Fall 2023 enrollment of PhD program, please apply at https://www.utc.edu/research/graduate-school/prospective-students/graduate-school-admissions

https://www.utc.edu/enrollment-management-and-student-affairs/center-for-global-education/international-student-and-scholar-services/prospective-students

https://www.utc.edu/sites/default/files/2021-03/how-to-apply-f12.pdf

 

The deadline for fall  application is July 1 (for students interested in graduate assistantship)

https://www.utc.edu/engineering-and-computer-science/academic-programs/electrical-engineering/graduate-curriculum/graduate-admission

 

For spring application, the website says Nov 1 as the deadline, but for assistantship, it is advised to complete application as earlier as possible. 

Our graduate school application requires GRE and TOEFL/IELTS scores.  For students with US degrees, please contact Lora Cook to verify whether foreign language exams might be waived. 

 

Thanks again for your interest. Please let me know if I can answer some of your questions,

 

Dear XYZ

 

Currently you have not submitted an application for our university.  Our PhD programs have a firm deadline for our PhD programs as noted below.  Degrees received from with the U.S. in the last two years will be waived from the English requirements.

Thank you for your interest in the University of Tennessee at Chattanooga. My name is Lora, and I will assist you in the application process. 

 

The following requirements must be fulfilled by February 1^st for the fall semestersand by September 1^st for spring semesters. We do not begin new students in the summer semester.

 

 

• Pay a nonrefundable application fee of $40.
• Submit the program-specific graduate admissions form. 
• Submit official transcripts from each college or university you have attended.  
• Report satisfactory English test scores from one of the three test scores (institution code 1831). TOEFL IBT minimum score: 79.  IELTS minimum score: 6. Duolingo minimum score 100.
• Submit a GRE score sheet, our institutional code is 1831.

• Submit a clear copy of your current passport.

 

 

Submit official proof of funding. may be submitted after acceptance by the program.   

 

PhD Program information.

 

Visit www.utc.edu/international for more information regarding housing, orientation, student fees, health insurance, and the admissions process.

 

If you have any questions, please don’t hesitate to ask.

Sincerely,

 

 

UTC independent research contract

 

You can submit the form from here

https://www.utc.edu/enrollment-management-and-student-affairs/registrar/individual-studies-contracts

Cloud computing, fog computing, and edge computing

 

Cloud computing, fog computing, and edge computing are three different approaches to processing and storing data from edge devices.

The main difference between cloud, fog and edge computing is defined by where data from edge devices is processed and stored. Cloud servers are placed away from the edge, while fog is pulled closer to reduce the time needed to process data and respond to events faster¹.

In cloud computing, data is processed on a central cloud server, which is usually located far away from the source of information³. Edge computing brings processing and storage systems as close as possible to the application, device, or component that generates and collects data. This helps minimize processing time by removing the need for transferring data to a central processing system and back to the endpoint².

Fog computing addresses this problem by inserting a processing layer between the edge and the cloud. This way, the ‘fog computer’ receives the data gathered at the edge and processes it before it reaches the cloud. Fog computing also differentiates between relevant and irrelevant data. While relevant data is sent to the cloud for storage, irrelevant data is either deleted or transmitted to the appropriate local platform².

Source: Conversation with Bing, 5/1/2023

(1) Differences Between Cloud, Fog and Edge Computing | Digiteum. https://www.digiteum.com/cloud-fog-edge-computing-iot/.

(2) Cloud, Fog, and Edge Computing: 3 Differences That Matter. https://dzone.com/articles/cloud-vs-fog-vs-edge-computing-3-differences-that.

(3) Edge Computing vs. Fog Computing: 10 Key Comparisons. https://www.spiceworks.com/tech/cloud/articles/edge-vs-fog-computing/.

(4) What's the Difference Between Cloud, Edge, and Fog Computing?. https://www.xenonstack.com/blog/cloud-edge-fog-computing.

(5) Edge & Cloud & Fog Computing: What Is The Difference Between Them. https://www.knowledgenile.com/blogs/edge-cloud-fog-computing-what-is-the-difference-between-them/.

Prompt-based training and fine-tuning training

 

Prompt-based training and fine-tuning training are two different approaches to customizing a pre-trained language model for a specific task.

Fine-tuning involves training a pre-trained model on a new dataset to improve its performance on a specific task. This customization step will let you get more out of the service by providing higher quality results than what you can get just from prompt design, the ability to train on more examples than can fit into a prompt, lower-latency requests and token savings due to shorter prompts². In particular, while prompts for base models often consist of multiple examples (few-shot learning), for fine-tuning, each training example generally consists of a single input example and its associated output, without the need to give detailed instructions or include multiple examples in the same prompt¹.

On the other hand, prompt-based training involves designing prompts that elicit the desired behavior from a pre-trained model without updating its weights. The main difference between pretrain-finetuning and prompt-tuning is that the former makes the model fit the downstream task, while the latter elicits the knowledge from the model by prompting³.

Source: Conversation with Bing, 5/1/2023

(1) How to customize a model with Azure OpenAI Service - Azure OpenAI. https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/fine-tuning.

(2) Fine-tuning - OpenAI API. https://platform.openai.com/docs/guides/fine-tuning.

(3) Brief Introduction to NLP Prompting | Finisky Garden. https://finisky.github.io/briefintrotoprompt.en/.

(4) Can prompt engineering methods surpass fine-tuning performance ... - Medium. https://medium.com/@lucalila/can-prompt-engineering-surpass-fine-tuning-performance-with-pre-trained-large-language-models-eefe107fb60e.

mac, convert pdf to docx in commandline

 

On a Mac computer, you can use the command line to convert a PDF file to a Word document by using the `textutil` command. Follow the steps below:

1. Open the Terminal application on your Mac. You can find it by searching for "Terminal" in Spotlight or navigating to Applications -> Utilities -> Terminal.

2. Navigate to the folder containing the PDF file you want to convert. You can use the `cd` command to change directories. For example, if your PDF file is located in the Documents folder, you can type `cd Documents` to navigate to that folder.

3. Once you're in the folder containing the PDF file, use the following command to convert the file to a Word document:

   `textutil -convert docx filename.pdf`

   Replace "filename.pdf" with the name of your PDF file.

4. Press Enter to run the command. The conversion process may take a few moments, depending on the size of the file.

5. Once the conversion is complete, you'll find a new file in the same folder with the same name as the original PDF file, but with a .docx extension. This is the Word document that was created from the PDF file.

That's it! You can now open the Word document in Microsoft Word or any other word processing application that supports the .docx file format.