Beyond Attention: Toward Machines with Intrinsic Higher Mental States

 

Beyond Attention: Toward Machines with Intrinsic Higher Mental States

https://techxplore.com/news/2025-05-architecture-emulates-higher-human-mental.html#google_vignette

USDA Rural-Urban Commuting Area Codes

 USDA

Rural-Urban Commuting Area Codes

https://www.ers.usda.gov/data-products/rural-urban-commuting-area-codes?utm_source=chatgpt.com

three digit 360 zipcode in Alabama

 Based on our discussion, I have looked further into the ‘360’ zipcode region, and found it contain 14 counties below:

 

counties = [    "Autauga County", "Barbour County", "Bullock County", "Butler County",

    "Chilton County", "Coosa County", "Covington County", "Crenshaw County",

    "Elmore County", "Lowndes County", "Macon County", "Montgomery County",

    "Pike County", "Tallapoosa County"]

 

Amon them, there are “Barbour”, “Bullock”, and “Macon” counties.

 

So, not sure how useful the three-digit zip code of ‘360’ might be relevant to TU MCH project. 

pastbin

 https://pastebin.com/uBcFUXCA

1. import pandas as pd
2. dataset = %env WORKSPACE_CDR
3. query = """
4. SELECT
5. p.person_id AS person_id,
6. c.concept_name AS state_name
7. FROM `{dataset}.person` AS p
8. LEFT JOIN `{dataset}.concept` AS c ON p.state_of_residence_concept_id = c.concept_id
9. WHERE c.concept_name LIKE 'PII State: %'
10. """
11.  
12. state_df = pd.read_gbq(query.format(dataset = dataset))
13.  
14. state_df['state_of_residence'] = state_df['state_name'].str.replace('PII State: ', '')
15.  
16. state_df.head()
17. state_df.shape
18.  
19. homeless_state_df=state_df[state_df['person_id'].isin(homeless_respiratory_status['person_id'])]
20. homeless_state_df['state_of_residence'].value_counts()

All of us research platform, data explore for rural health research.

 All of us research platform, data explore for rural health research.

Zip3, observational table

Workspaces > Beginner Intro to AoU Data and the Workbench > Analysis >

00. Overview of Data Analysis Steps in AoU

In ‘test-state_data_v060523’, found sample on state, county, and zip3.

 

 

ODU CS and DSC courses taught by Hong Qin

 

https://catalog.odu.edu/courses/cs/#graduatecoursestext

https://catalog.odu.edu/courses/dasc/

CS 781  AI for Health Sciences  (3 Credit Hours)  

This course explores the application of AI in health sciences, focusing on machine learning, NLP, computer vision, generative AI techniques for diagnostics, treatment planning, patient monitoring, and biomedical research. It covers precision medicine, ethical AI, and the integration of AI into practice. Students will gain a deep understanding and practical skills to develop innovative AI solutions that address real-world challenges in health sciences.

Prerequisites: Prior programming experience  

CS 782  Generative AI  (3 Credit Hours)  

This course provides a deep dive into the foundations and current advancements in generative AI. It covers key concepts such as transformer models, GANs, VAEs, LLMs, and their applications across various fields, emphasizing both theory and hands-on learning, including ethical considerations such as fairness and bias mitigation. Students will develop a comprehensive understanding of generative AI and gain practical experience.

Prerequisites: Prior programming experience  

CS 881  AI for Health Sciences  (3 Credit Hours)  

This course explores the application of AI in health sciences, focusing on machine learning, NLP, computer vision, generative AI techniques for diagnostics, treatment planning, patient monitoring, and biomedical research. It covers precision medicine, ethical AI, and the integration of AI into practice. Students will gain a deep understanding and practical skills to develop innovative AI solutions that address real-world challenges in health sciences.

Prerequisites: Prior programming experience  

CS 882  Generative AI  (3 Credit Hours)  

This course provides a deep dive into the foundations and current advancements in generative AI. It covers key concepts such as transformer models, GANs, VAEs, LLMs, and their applications across various fields, emphasizing both theory and hands-on learning, including ethical considerations such as fairness and bias mitigation. Students will develop a comprehensive understanding of generative AI and gain practical experience.

Prerequisites: Prior programming experience  

DASC 781  AI for Health Sciences  (3 Credit Hours)  

This course explores the application of AI in health sciences, focusing on machine learning, NLP, computer vision, generative AI techniques for diagnostics, treatment planning, patient monitoring, and biomedical research. It covers precision medicine, ethical AI, and the integration of AI into practice. Students will gain a deep understanding and practical skills to develop innovative AI solutions that address real-world challenges in health sciences.

Prerequisites: Prior programming experience  

DASC 782  Generative AI  (3 Credit Hours)  

This course provides a deep dive into the foundations and current advancements in generative AI. It covers key concepts such as transformer models, GANs, VAEs, LLMs, and their applications across various fields, emphasizing both theory and hands-on learning, including ethical considerations such as fairness and bias mitigation. Students will develop a comprehensive understanding of generative AI and gain practical experience.

Prerequisites: Prior programming experience  

DASC 881  AI for Health Sciences  (3 Credit Hours)  

This course explores the application of AI in health sciences, focusing on machine learning, NLP, computer vision, generative AI techniques for diagnostics, treatment planning, patient monitoring, and biomedical research. It covers precision medicine, ethical AI, and the integration of AI into practice. Students will gain a deep understanding and practical skills to develop innovative AI solutions that address real-world challenges in health sciences.

Prerequisites: Prior programming experience  

DASC 882  Generative AI  (3 Credit Hours)  

This course provides a deep dive into the foundations and current advancements in generative AI. It covers key concepts such as transformer models, GANs, VAEs, LLMs, and their applications across various fields, emphasizing both theory and hands-on learning, including ethical considerations such as fairness and bias mitigation. Students will develop a comprehensive understanding of generative AI and gain practical experience.

Prerequisites: Prior programming experience  

logit, sigmoid function, and probability

step-by-step through how the sigmoid function turns a logit into a probability, with both math and plain English at each step.

---

✅ Step 1: What is a logit?

The logit of a probability $p$ is defined as:

$$\text{logit}(p) = \log\left(\frac{p}{1 - p}\right)$$

This is called the log-odds, because it’s the natural log of the odds.

---

✅ Step 2: What if we are given the logit and want to get the probability?

Let’s say we are given a number $x$, and we know it’s a logit.

That means:

$$x = \log\left(\frac{p}{1 - p}\right)$$

We want to solve for $p$, the probability.

---

✅ Step 3: Exponentiate both sides

To get rid of the logarithm, we exponentiate both sides:

$$e^x = \frac{p}{1 - p}$$

This tells us the odds in terms of $x$.

---

✅ Step 4: Solve for $p$

Now we solve this equation for $p$.

Start with:

$$e^x = \frac{p}{1 - p}$$

Multiply both sides by $1 - p$:

$$e^x (1 - p) = p$$

Distribute the left-hand side:

$$e^x - e^x p = p$$

Now get all the $p$'s on one side:

$$e^x = p + e^x p$$

Factor out $p$ on the right-hand side:

$$e^x = p(1 + e^x)$$

Now divide both sides by $1 + e^x$:

$$p = \frac{e^x}{1 + e^x}$$

---

✅ Step 5: Simplify into the sigmoid form

We now simplify that expression:

$$p = \frac{e^x}{1 + e^x} = \frac{1}{\frac{1 + e^x}{e^x}} = \frac{1}{1 + e^{-x}}$$

That’s the sigmoid function:

$$p = \sigma(x) = \frac{1}{1 + e^{-x}}$$

---

✅ Final Result

So if you’re given a logit value $x$, the sigmoid function:

$$\sigma(x) = \frac{1}{1 + e^{-x}}$$

turns it into a probability $p \in (0, 1)$.

---

🔁 Why this is useful

• In logistic regression, we compute:

  $$x = w^T x + b \quad \text{(a linear score)}$$

• Then use the sigmoid to convert that score (logit) into a probability of class 1:

  $$p = \frac{1}{1 + e^{-x}}$$

This way, the model’s output is interpretable as a probability — suitable for binary classification.

Let me know if you want a plot or visualization to make it even clearer!

ICDM 2025 DC

The 25th IEEE International Conference on Data Mining (IEEE ICDM 2025) includes half- or full-day workshops

https://www3.cs.stonybrook.edu/~icdm2025/cfw.html

https://2025-icdm-ughs.github.io/

https://wi-lab.com/cyberchair/2025/icdm25/scripts/submit.php?subarea=S01&undisplay_detail=1&wh=/cyberchair/2025/icdm25/scripts/ws_submit.php

Main conference

• Full paper submissions: June 6, 2025
• Notifications to authors: August 25, 2025
• Camera ready: September 25, 2025

Workshops

• March 14, 2025: Workshop proposals deadline
• April 11, 2025: Workshop proposals notification
• September 1, 2025: Workshop paper submission deadline
• Camera ready: September 25, 2025

Tutorials

• Tutorial proposal due: September 5, 2025
• Notification: September 26, 2025

Demonstrations

• Demo paper submission: Friday, September 05, 2025
• Notification to authors: Friday, September 26, 2025

Undergraduate and High School Symposium

• Paper Submission Deadline: Sep 1, 2025 11:59 PM AoE
• Notification of Acceptance: Oct 1, 2025
• Camera-Ready Paper Submission: Oct 15, 2025

Hotel

Important Dates:

• Room Block Cut-Off Date is October 18, 2025.

All submission deadlines are end-of-day in the Anywhere on Earth (AoE) time zone.

AAAI focus groups

 In the AAAI 

1. AIIDE – Artificial Intelligence and Interactive Digital Entertainment: Focuses on AI in games and entertainment media.

2. EAAI – Educational Advances in Artificial Intelligence: Emphasizes AI education, especially innovative teaching techniques and curricula.

3. FLAIRS – Florida Artificial Intelligence Research Society Conference: A regional AI conference that covers a broad spectrum of AI research.

4. HCOMP – Human Computation and Crowdsourcing: Explores systems that rely on human intelligence, often combined with AI (e.g., crowdsourced labeling).

5. IAAI – Innovative Applications of Artificial Intelligence: Focuses on real-world applications and deployed AI systems.

6. ICAPS – International Conference on Automated Planning and Scheduling: Covers planning, scheduling, and decision-making problems.

7. ICWSM – International Conference on Web and Social Media: Focuses on computational social science and data-driven studies of social media.

8. KR – Principles of Knowledge Representation and Reasoning: Covers formal representations of knowledge and reasoning mechanisms.

9. UAI – Uncertainty in Artificial Intelligence: Emphasizes probabilistic reasoning, Bayesian networks, and managing uncertainty in AI systems.

odurf sponsored project

 ODURF project reports -> Project ID -> transaction + view report. 

https://hera.odurf.odu.edu/RFPortal/Reports/

ODURF reimbursement form

 you can pay with a credit card and seek reimbursement using this form here: Consultant-Honorarium-Reimbursement-Form.pdf

Microsoft Generative AI Teaching Materials

 

Microsoft Generative AI Teaching Materials

Microsoft offers a wide range of generative AI teaching resources designed for educators, trainers, and students at all skill levels. These materials cover foundational concepts, practical applications, and responsible use of generative AI tools in educational settings.

Key Resources and Learning Paths

• Introduction to Generative AI for Trainers
  This learning path is tailored for educators and trainers, focusing on how to leverage generative AI tools like Microsoft Copilot to create engaging educational materials. It covers prompt engineering, responsible AI use, and practical demonstrations for classroom support, including lesson creation and student assistance4.

• MSLE Generative AI for Teaching Bootcamp
  A 6-hour bootcamp specifically for educators (K-12, higher education, technical colleges) that teaches how to use AI tools to develop syllabi, lesson plans, quizzes, assignments, and grading rubrics. It includes collaborative projects, effective prompting techniques, and access to resources via the Microsoft Learn for Educators program5.

• Microsoft Learn: Generative AI Fundamentals and Applications
  Multiple beginner-friendly modules and learning paths introduce the core concepts of generative AI, language models, prompt engineering, and responsible AI practices. These are suitable for AI engineers, developers, solution architects, and students, with hands-on activities using Azure OpenAI Service12.

• Generative AI for Beginners (Video Series and Course)
  A comprehensive, multi-lesson course and video series led by Microsoft Cloud Advocates. It covers the fundamentals of building generative AI applications, including large language models (LLMs), practical use cases in education, and creative applications like AI-powered image generation368.

• AI for Education Resource Hub
  The Microsoft Learn Educator Center provides a centralized collection of resources, including:

  • Free AI tools for educators

  • Guidance on using Microsoft Copilot in the classroom

  • AI classroom toolkits for responsible and safe use

  • Prompt libraries for lesson creation

  • Technical and non-technical learning paths for both teachers and students7.

Highlighted Features and Topics

• Creating interactive and personalized learning materials with AI

• Using Copilot to assist with administrative and teaching tasks

• Responsible AI practices and minimizing risks in content generation

• Prompt engineering for effective AI use in education

• Practical demonstrations and collaborative educator communities

How to Access

All resources are available through the Microsoft Learn platform, with many materials requiring only a free Microsoft account. Some advanced content may require familiarity with Azure or participation in educator-specific programs12457.

Summary Table: Main Microsoft Generative AI Teaching Resources

Resource/Program	Audience	Focus Areas	Format
Introduction to Generative AI for Trainers	Educators	Copilot, prompt engineering, AI in teaching	Learning path
MSLE Generative AI for Teaching Bootcamp	Educators	Syllabus, lesson plans, quizzes, grading	Bootcamp
Generative AI Fundamentals (Microsoft Learn)	All levels	Core AI concepts, responsible AI, Azure OpenAI	Modules, courses
Generative AI for Beginners (Course/Video Series)	Beginners	Building apps, LLMs, practical use cases	Course, videos
AI for Education Resource Hub	Educators/Students	Tools, toolkits, prompt libraries, Copilot	Resource hub

These resources equip educators with the knowledge and tools to integrate generative AI into their teaching, streamline tasks, and create more engaging, personalized learning experiences457.

Citations:

1. https://learn.microsoft.com/en-us/training/modules/fundamentals-generative-ai/
2. https://learn.microsoft.com/en-us/training/paths/introduction-generative-ai/
3. https://microsoft.github.io/generative-ai-for-beginners/
4. https://learn.microsoft.com/en-us/training/paths/intro-generative-ai-for-trainers/
5. https://learn.microsoft.com/en-us/training/courses/msle-generative-ai-for-teaching-bootcamp
6. https://learn.microsoft.com/en-us/shows/generative-ai-for-beginners/
7. https://learn.microsoft.com/en-us/training/educator-center/topics/ai-for-education
8. https://learn.microsoft.com/en-us/shows/generative-ai-for-beginners/introduction-to-generative-ai-and-llms-generative-ai-for-beginners
9. https://learn.microsoft.com/en-us/ai/

---

Answer from Perplexity: pplx.ai/share

Here are the main GitHub repositories for Microsoft’s generative AI teaching materials:

• Generative AI for Beginners (21 Lessons, Python & TypeScript)
  Comprehensive course with 21 lessons covering fundamentals, prompt engineering, responsible AI, and hands-on projects.
  [https://github.com/microsoft/generative-ai-for-beginners][1]

• Generative AI for Beginners (12-Lesson Version)
  A condensed 12-lesson course, also created by Microsoft Cloud Advocates, focusing on core generative AI concepts and application building.
  [https://github.com/html5cat/msft-generative-ai][3]

• AI for Beginners
  Broader 12-week, 24-lesson curriculum on artificial intelligence, suitable for those seeking foundational AI knowledge before diving into generative AI specifics.
  [https://github.com/microsoft/AI-For-Beginners][2]

• Generative AI with JavaScript
  Course focused on integrating generative AI into JavaScript applications, with lessons and code samples for web developers.
  [https://github.com/microsoft/generative-ai-with-javascript][7]

These repositories provide open-source curricula, code samples, setup guides, and community support for educators and learners interested in generative AI.1237

Citations:

1. https://github.com/microsoft/generative-ai-for-beginners
2. https://github.com/microsoft/AI-For-Beginners
3. https://github.com/html5cat/msft-generative-ai
4. https://learn.microsoft.com/en-us/shows/generative-ai-for-beginners/
5. https://techcommunity.microsoft.com/blog/educatordeveloperblog/generative-ai-for-beginners---a-12-lesson-course/3968583
6. https://learn.microsoft.com/en-us/training/courses/msle-generative-ai-for-teaching-bootcamp
7. https://github.com/microsoft/generative-ai-with-javascript
8. https://www.sunsetlearning.com/microsoft-learn-for-educators-program/
9. https://www.udemy.com/course/bootcamp-generative-artificial-intelligence-and-llm-app-development/

---

Answer from Perplexity: pplx.ai/share