Monday, 24 June 2024

ICSSR FUNDED TEN DAYS RESEARCH METHODOLOGY COURSE - FDP 27.06.2024 @MBA, AU

Good Afternoon!!!

Let us Begin!!!☝

AI tools for Research Methodolgy

Agenda



Research:

Systematic investigation into and study of materials and sources in order to establish facts and reach new conclusions













GenAI

Generative AI, sometimes called gen AI, is artificial intelligence (AI) that can create original content—such as text, images, video, audio or software code—in response to a user’s prompt or request

ATTENTION IS ALL I NEED
All is AI, AI is ALL
RM through AI, AI 4 RM


Profile  

Academic Identities


 

https://scholar.google.com/citations?hl=en&user=Oap3Yg4AAAAJ
IRINS - Indian Research Information Network Systems
https://irins.inflibnet.ac.in/irins/ 
Scholar:
citation
h-index
i10-index

Sure, bro! Here's a simple breakdown:
### Citation
- **Definition:** A reference to a published or unpublished source.
- **Importance:** Shows the impact and relevance of a research work by how often it is referred to by others.
### h-index
- **Definition:** A metric that measures both the productivity and citation impact of a researcher's publications.
- **Calculation:** An h-index of \( h \) means a researcher has \( h \) papers with at least \( h \) citations each. For example, if you have 5 papers, each cited at least 5 times, your h-index is 5.
- **Importance:** Balances quantity (number of papers) and quality (citations per paper).
### i10-index
- **Definition:** The number of publications with at least 10 citations.
- **Calculation:** Count the number of papers that have been cited at least 10 times.
- **Importance:** Easy way to see how many significant contributions a researcher has made.
### Why They Are Important
1. **Evaluation:** Helps in evaluating the research impact and influence of a researcher.
2. **Funding:** Can influence funding decisions and grant applications.
3. **Academic Promotions:** Used in academic evaluations for promotions and tenure.
These metrics help to gauge the quality and impact of research work in the academic community.

Sure, bro! Here are numerical examples for both h-index and i10-index:
### h-index
**Example:**
Let's say a researcher has the following 7 papers with these citation counts:
- Paper 1: 20 citations
- Paper 2: 15 citations
- Paper 3: 10 citations
- Paper 4: 8 citations
- Paper 5: 5 citations
- Paper 6: 3 citations
- Paper 7: 2 citations
To find the h-index:
1. **Sort the papers by citation count (highest to lowest):** 20, 15, 10, 8, 5, 3, 2.
2. **Determine the highest number \( h \) such that the researcher has \( h \) papers with at least \( h \) citations each.**
   Here:
   - The 1st paper has 20 citations (≥1).
   - The 2nd paper has 15 citations (≥2).
   - The 3rd paper has 10 citations (≥3).
   - The 4th paper has 8 citations (≥4).
   - The 5th paper has 5 citations (≥5).
   - The 6th paper has 3 citations (<6). 
Since the 6th paper doesn't meet the criteria (it needs at least 6 citations to count), the **h-index** is 5.
### i10-index
**Example:**
Let's consider the same researcher with the following papers:
- Paper 1: 20 citations
- Paper 2: 15 citations
- Paper 3: 10 citations
- Paper 4: 8 citations
- Paper 5: 5 citations
- Paper 6: 3 citations
- Paper 7: 2 citations
To find the i10-index:
1. **Count the number of papers with at least 10 citations.**
   Here:
   - Paper 1: 20 citations (≥10)
   - Paper 2: 15 citations (≥10)
   - Paper 3: 10 citations (≥10)
   - Paper 4: 8 citations (<10)
   - Paper 5: 5 citations (<10)
   - Paper 6: 3 citations (<10)
   - Paper 7: 2 citations (<10)
Only Papers 1, 2, and 3 have 10 or more citations. So, the **i10-index** is 3.
### Summary
- **h-index:** Measures the number of papers (h) with at least h citations each.
  - Example: h-index is 5.
- **i10-index:** Measures the number of papers with at least 10 citations each.
  - Example: i10-index is 3.
These indices help in evaluating the research impact by balancing the quantity and quality of a researcher's publications.
-----------------------------------------------------------------------------------------------------------------------------

Artificial Intelligence - Generative AI 

Generative AI: A subset of artificial intelligence that uses algorithms to generate new, original content based on the patterns and structures it has learned from training data.

  1. Types of Content:

  2. How It Works:

  3. Applications:

Generative AI is transforming how we create and interact with digital content, offering vast possibilities across various fields.

Key Points
  • Text: Creates articles, stories, or code (e.g., GPT models).
  • Images: Generates artwork or realistic photos (e.g., DALL-E).
  • Audio: Produces music or realistic voice recordings.
  • Video: Creates or alters video content.
  • Training Data: The AI is trained on large datasets relevant to the type of content it aims to generate.
  • Algorithms: Uses deep learning techniques, particularly neural networks, to learn from the data.
  • Generation: Once trained, it can produce new content that mimics the style and structure of the original data.
  • Creative Arts: Producing art, music, and literature.
  • Business: Automating content creation, such as marketing materials and reports.
  • Technology: Enhancing user experiences with chatbots and virtual assistants.
  • Entertainment: Creating video game graphics, animations, and special effects.
Example
  • Text Generation: OpenAI's GPT-4 can write essays, answer questions, and even generate poetry.
  • Image Generation: DALL-E can create images from textual descriptions, like "a two-story pink house shaped like a shoe."
  • Research Design,  Literature Survey, Writing, Grammar,Illustrations, Data Analysis
Importance
  • Innovation: Drives new forms of creativity and content creation.
  • Efficiency: Automates repetitive tasks, saving time and resources.
  • Personalization: Enables tailored content and experiences for users.
LLM blog

Prompt Engineering

Research Design : Blog page For AI  for for RM

 https://ametodl.blogspot.com/2024/06/research-methodology-with-chatgpt-1.html




Find Research Articles
🔗 Elicit: https://elicit.org/  - Simple to use
🔗 Scite.AI Assistant: https://bit.ly/scigradcoach-sciteai - Not working?
🔗 Perplexity AI: https://www.perplexity.ai/ Where knowlwdge begins
🔗 Research Rabbit: https://www.researchrabbit.ai/        Find citation, relevance, author, Keyword search https://doi.org/10.1016/j.comnet.2010.12.008
🔗 LitMaps: https://www.litmaps.com/  Find the right papers faster
🔗 Connected Papers: https://www.connectedpapers.com/

Summarize Research Articles
🔗 TLDR This: https://tldrthis.com/
🔗 Paper Digest: https://www.paper-digest.com/
🔗 Resoomer: https://resoomer.com/en/
🔗 Elicit: https://elicit.org/
🔗 SciSpace Co-Pilot: https://www.typeset.io/?via=nTKwM1OBBQs
🔗 Sharly.AI: https://www.sharly.ai/
🔗 WordTune Read: https://www.wordtune.com/read
🔗 Scholarcy:  https://www.scholarcy.com/
Editing Research and Review Articles
🔗 Grammarly: http://bit.ly/grammarlyscigradcoach
🔗 ChatGPT: https://chat.openai.com/    
🔗 Sharly.AI: https://www.sharly.ai/

AI/SI/Plagiarism Checkers


Paraphrasing Tools

QUILL BOT : https://quillbot.com/ [Recommented & Preferred]

Technique: ICQP

Identify/Interchange
Cite
Quote
Paraphrase/Rewrite



You Tube for ChatGPT - Introduction : 


Blog page For AI for RM


WALK THROUGH 

AI4RM  Quiz


-----------------------------------------------------------------------------------------------------------------------------
Case Study:
=======
Make money through Social Media
Social Media marketing
Stunning UI to engage target audience
Quality of Content
Frequency of Visit

Research Support:
Converting older code languages to newer ones for application modernization and migration
Generating context-aware code
Speeding data analysis

Top Searc/Research Tools

1. Google Scholar – Google Scholar is a search engine for scholarly literature, including articles, theses, books, and conference papers.

2. JSTOR – JSTOR is a digital library of academic journals, books, and primary sources.

3.PubMed – PubMed is a free search engine accessing primarily the MEDLINE database of references and abstracts on life sciences and biomedical topics. 

4. Web of Science: Web of Science is a citation index that allows you to search for articles, conference proceedings, and books across various scientific disciplines. 

5. Scopus – Scopus citation database that covers scientific, technical, medical, and social sciences literature. 

6. Zotero: Zotero is a free, open-source citation management tool that helps you organize your research sources, create bibliographies, and collaborate with others.

7. Mendeley – Mendeley is a reference management software that allows you to organize and share your research papers and collaborate with others.

8. EndNote – EndNote is a software tool for managing bibliographies, citations, and references on the Windows and macOS operating systems. 

9. RefWorks – RefWorks is a web-based reference management tool that allows you to create and organize a personal database of references and generate citations and bibliographies.

10. Evernote – Evernote is a digital notebook that allows you to capture and organize your research notes, web clippings, and documents.

11. SPSS – SPSS is a statistical software package used for data analysis, data mining, and forecasting.

12. R – R is a free, open-source software environment for statistical computing and graphics.

Other helpful tools for collaboration and organization include NVivo, Slack, Zoom, and Microsoft Teams.

With these tools, researchers can effectively find relevant literature, manage references, analyze data, write research papers, create visual representations of data, and collaborate with peers. 

Qualtrics – Qualtrics is an online survey platform that allows researchers to design and distribute surveys, collect and analyze data, and generate reports.

Research Tools 

Comparison of 10 AI tools


-----------------------------------------------------------------------------------------------------------------------------


- No comments:

Sunday, 23 June 2024

Canva Apps - Great !

 New Canva Apps that excited me!


Heygen

Image animate

Coloring Book

Font Frame

Flower Artist ( 5 credits/day)

Image upscaler

Neon Artist

Colorize

Ultra Real




- No comments:

Friday, 21 June 2024

Prompting Techniques in NutShell

Prompting Techniques


1. Chain-of-thought (CoT) prompting

2. Generated knowledge prompting

3. Least-to-most prompting

4. Self-consistency decoding

5. Complexity-based prompting

6. Self-refine

7. Tree-of-thought prompting

8. Maieutic prompting

9. Directional-stimulus prompting

10. Textual inversion and embeddings

11. Using gradient descent to search for prompts

12. Prompt injection


Copilot:

Certainly! Let's explore examples for each of the prompt techniques you've mentioned:

1. **Chain-of-Thought (CoT) Prompting**:

   - In CoT prompting, you build a sequence of prompts that guide the model's thinking process. For instance:

     - Initial prompt: "Describe the life cycle of a butterfly."

     - Follow-up prompt: "Now explain how metamorphosis impacts the ecosystem."

2. **Generated Knowledge Prompting**:

   - This technique involves asking the model to generate new information. Examples include:

     - Prompt: "Provide three lesser-known facts about the Eiffel Tower."

     - Prompt: "What are the benefits of using solar energy?"

3. **Least-to-Most Prompting**:

   - Start with minimal information and gradually increase complexity. For instance:

     - Minimal prompt: "Write a short summary of World War II."

     - More detailed prompt: "Now elaborate on the impact of the Battle of Stalingrad."

4. **Self-Consistency Decoding**:

   - Ensure the model's responses remain consistent. Example:

     - Prompt: "Explain the concept of entropy in thermodynamics."

5. **Complexity-Based Prompting**:

   - Adjust the prompt complexity based on the model's performance. For example:

     - Simple prompt: "Define photosynthesis."

     - Complex prompt: "Discuss the role of chlorophyll in the photosynthetic process."

6. **Self-Refine**:

   - Iteratively refine the prompt to get desired output. Example:

     - Initial prompt: "Summarize the plot of 'Pride and Prejudice.'"

     - Refinement: "Now focus on Elizabeth Bennet's character development."

7. **Tree-of-Thought Prompting**:

   - Create branching prompts to explore different aspects. For instance:

     - Prompt: "Describe the impact of climate change on coral reefs."

     - Branch 1: "Discuss ocean acidification."

     - Branch 2: "Explain coral bleaching."

8. **Maieutic Prompting**:

   - Ask questions to help the model discover insights. Example:

     - Prompt: "What are the implications of AI ethics?"

     - Follow-up: "Consider privacy concerns and bias."

9. **Directional-Stimulus Prompting**:

   - Use specific cues to guide the model. Example:

     - Prompt: "Imagine you're a detective investigating a murder."

     - Stimulus: "You find a mysterious letter at the crime scene."

10. **Textual Inversion and Embeddings**:

    - Invert text or manipulate embeddings. Example:

      - Prompt: "Reverse the order of this sentence: 'The cat chased the mouse.'"

11. **Using Gradient Descent to Search for Prompts**:

    - Optimize prompts using gradient-based methods. Example:

      - Start with a random prompt and iteratively improve it.

12. **Prompt Injection**:

    - Inject specific information into the prompt. Example:

      - Initial prompt: "Write a poem about love."

      - Injection: "Incorporate the theme of longing and loss."


Remember, these techniques allow us to tailor interactions with language models for specific tasks and outcomes¹²³. Feel free to explore further or ask for more examples! 😊

Source: Conversation with Copilot, 6/22/2024

(1) Prompting Techniques | Prompt Engineering Guide. https://www.promptingguide.ai/techniques.

(2) Prompt engineering guide: Techniques, examples, and use cases - Pluralsight. https://www.pluralsight.com/resources/blog/data/prompt-engineering-techniques.

(3) The Prompt Report: A Systematic Survey of Prompting Techniques - arXiv.org. https://arxiv.org/html/2406.06608v1.

(4) 18 Prompting Examples (2024) - Helpful Professor. https://helpfulprofessor.com/prompting-examples/.

ChatGPT:

1. **Chain-of-Thought (CoT) Prompting**:

   - **Prompt**: "What is the total cost of 3 apples and 2 bananas if apples cost $1 each and bananas cost $0.50 each? Let's break down the problem step by step."

   - **Response**: "First, calculate the cost of 3 apples: 3 * $1 = $3. Next, calculate the cost of 2 bananas: 2 * $0.50 = $1. Finally, add the costs together: $3 + $1 = $4. The total cost is $4."

2. **Generated Knowledge Prompting**:

   - **Prompt**: "Explain how photosynthesis works. What basic knowledge do we need?"

   - **Response**: "Photosynthesis is a process used by plants to convert light energy into chemical energy. Basic knowledge includes understanding that plants use sunlight, carbon dioxide, and water to produce glucose and oxygen."

3. **Least-to-Most Prompting**:

   - **Prompt**: "Solve a simple algebra equation first: What is x if 2x = 4? Now, solve this: What is x in the equation 2x + 3 = 7?"

   - **Response**: "First equation: 2x = 4, so x = 2. Second equation: 2x + 3 = 7. Subtract 3 from both sides: 2x = 4, so x = 2."

4. **Self-Consistency Decoding**:

   - **Prompt**: "Is the capital of France Paris or London? Explain why."

   - **Response**: "The capital of France is Paris. Paris is the largest city in France and has been the country's capital since the 10th century. It is known for landmarks like the Eiffel Tower and the Louvre Museum."

5. **Complexity-Based Prompting**:

   - **Prompt**: "First, describe what an atom is. Then, explain how atoms form molecules."

   - **Response**: "An atom is the smallest unit of matter that retains the properties of an element. Atoms form molecules by sharing or transferring electrons through chemical bonds."

6. **Self-Refine**:

   - **Prompt**: "Write a brief description of the water cycle. Then refine it to include the terms evaporation, condensation, and precipitation."

   - **Initial Response**: "The water cycle describes how water moves through the environment."

   - **Refined Response**: "The water cycle describes how water moves through the environment, involving processes like evaporation (water turning into vapor), condensation (vapor turning into clouds), and precipitation (water falling as rain or snow)."

7. **Tree-of-Thought Prompting**:

   - **Prompt**: "Should we build a new park in the city? Consider the benefits and drawbacks."

   - **Response**: "Benefits include more recreational space, improved mental health, and increased property values. Drawbacks include cost, maintenance, and potential displacement of current land use. Weighing these factors, we can decide if the benefits outweigh the drawbacks."

8. **Maieutic Prompting**:

   - **Prompt**: "Why do you think democracy is important? Can you think of reasons why it might have weaknesses?"

   - **Response**: "Democracy is important because it allows citizens to have a say in their government, promoting freedom and equality. However, it can have weaknesses like the risk of populism, where leaders might make popular but harmful decisions."

9. **Directional-Stimulus Prompting**:

   - **Prompt**: "What are the advantages of renewable energy sources like solar and wind power?"

   - **Response**: "Renewable energy sources like solar and wind power are advantageous because they reduce greenhouse gas emissions, decrease dependence on fossil fuels, and provide sustainable energy. Additionally, they create jobs in new industries and reduce air pollution."

10. **Textual Inversion and Embeddings**:

    - **Prompt**: "What does the phrase 'break the ice' mean?"

    - **Response**: "The phrase 'break the ice' means to initiate conversation in a social setting, making people feel more comfortable and relaxed."

11. **Using Gradient Descent to Search for Prompts**:

    - **Prompt**: This involves an algorithmic approach rather than a simple text example. However, a simplified version could be:

    - **Example**: "Optimize the question 'What are the benefits of exercise?' to find the most effective way to elicit detailed responses."

    - **Optimized Prompt**: "Can you list the physical, mental, and social benefits of regular exercise, and provide examples for each category?"

12. **Prompt Injection**:

    - **Prompt**: "Tell me about the history of AI. Please ensure your response includes the invention of neural networks and the development of deep learning."

    - **Response**: "The history of AI includes significant milestones such as the invention of neural networks in the 1950s and the development of deep learning in the 2010s. These advancements have enabled significant progress in machine learning and artificial intelligence."

These examples demonstrate how each prompting technique can be applied to guide large language models towards producing more accurate, relevant, and detailed responses.

Perplexity AI:

Here are example prompts for each of the prompting techniques mentioned:

1. **Chain-of-Thought (CoT) Prompting**:

   - **Example Prompt**:

     ```plaintext

     The odd numbers in this group add up to an even number: 4, 8, 9, 15, 12, 2, 1.

     A: Adding all the odd numbers (9, 15, 1) gives 25. The answer is False.

     The odd numbers in this group add up to an even number: 17, 10, 19, 4, 8, 12, 24.

     A: Adding all the odd numbers (17, 19) gives 36. The answer is True.

     The odd numbers in this group add up to an even number: 16, 11, 14, 4, 8, 13, 24.

     A: Adding all the odd numbers (11, 13) gives 24. The answer is True.

     The odd numbers in this group add up to an even number: 17, 9, 10, 12, 13, 4, 2.

     A: Adding all the odd numbers (17, 9, 13) gives 39. The answer is False.

     The odd numbers in this group add up to an even number: 15, 32, 5, 13, 82, 7, 1.

     A: Adding all the odd numbers (15, 5, 13, 7, 1) gives 41. The answer is False.

     ```

   - **Output**:

     ```plaintext

     Adding all the odd numbers (15, 5, 13, 7, 1) gives 41. The answer is False.

     ```


2. **Generated Knowledge Prompting**:

   - **Example Prompt**:

     ```plaintext

     What is the capital of France?

     ```

   - **Output**:

     ```plaintext

     The capital of France is Paris.

     ```


3. **Least-to-Most Prompting**:

   - **Example Prompt**:

     ```plaintext

     To solve the math word problem, break it down into simpler subproblems. What is the cost of the first item?

     ```

   - **Output**:

     ```plaintext

     The cost of the first item is $10.

     ```


4. **Self-Consistency Decoding**:

   - **Example Prompt**:

     ```plaintext

     Please explain how you arrived at your answer.

     ```

   - **Output**:

     ```plaintext

     I arrived at my answer by adding the numbers 2 and 3.

     ```


5. **Complexity-Based Prompting**:

   - **Example Prompt**:

     ```plaintext

     Please solve this math problem step by step. What is the result of 2 + 3?

     ```

   - **Output**:

     ```plaintext

     First, I add 2 and 3. The result is 5.

     ```


6. **Self-Refine**:

   - **Example Prompt**:

     ```plaintext

     Please refine your answer to make it more accurate.

     ```

   - **Output**:

     ```plaintext

     I refined my answer by adding more details. The result of 2 + 3 is 5.

     ```


7. **Tree-of-Thought Prompting**:

   - **Example Prompt**:

     ```plaintext

     Please break down your thought process into a tree structure. What is the result of 2 + 3?

     ```

   - **Output**:

     ```plaintext

     Here is the tree structure:

     - 2 + 3

     - 2 + 3 = 5

     ```


8. **Maieutic Prompting**:

   - **Example Prompt**:

     ```plaintext

     Please guide me through your thought process. What is the result of 2 + 3?

     ```

   - **Output**:

     ```plaintext

     Here is my thought process:

     - 2 + 3

     - 2 + 3 = 5

     ```


9. **Directional-Stimulus Prompting**:

   - **Example Prompt**:

     ```plaintext

     Please follow these steps to solve the problem. What is the result of 2 + 3?

     ```

   - **Output**:

     ```plaintext

     Here are the steps:

     - 2 + 3

     - 2 + 3 = 5

     ```


10. **Textual Inversion and Embeddings**:

    - **Example Prompt**:

      ```plaintext

      Please describe the steps to solve the math problem. What is the result of 2 + 3?

      ```

    - **Output**:

      ```plaintext

      Here are the steps:

      - 2 + 3

      - 2 + 3 = 5

      ```


11. **Using Gradient Descent to Search for Prompts**:

    - **Example Prompt**:

      ```plaintext

      Please optimize the prompt to get the best result. What is the result of 2 + 3?

      ```

    - **Output**:

      ```plaintext

      The optimized prompt is: "What is the result of 2 + 3?"

      ```


12. **Prompt Injection**:

    - **Example Prompt**:

      ```plaintext

      Please inject the prompt into the model. What is the result of 2 + 3?

      ```

    - **Output**:

      ```plaintext

      The result of 2 + 3 is 5.

      ```


13. **Using Gradient Descent to Search for Prompts**:

    - **Example Prompt**:

      ```plaintext

      Please optimize the prompt to get the best result. What is the result of 2 + 3?

      ```

    - **Output**:

      ```plaintext

      The optimized prompt is: "What is the result of 2 + 3?"

      ```


14. **Prompt Injection**:

    - **Example Prompt**:

      ```plaintext

      Please inject the prompt into the model. What is the result of 2 + 3?

      ```

    - **Output**:

      ```plaintext

      The result of 2 + 3 is 5.

      ```

These prompts demonstrate how each technique can be used to elicit specific responses from large language models. They are designed to guide the models through complex reasoning tasks, improve their accuracy, and enhance their ability to provide detailed explanations[1][2][3][4].

Citations:

[1] https://www.promptingguide.ai/techniques/cot

[2] https://www.techtarget.com/searchenterpriseai/definition/chain-of-thought-prompting

[3] https://www.mercity.ai/blog-post/guide-to-chain-of-thought-prompting

[4] https://pub.towardsai.net/chain-of-thought-prompting-thats-how-the-models-think-6e31a5844a32?gi=105f92fd5b81

[5] https://learnprompting.org/docs/intermediate/chain_of_thought


- No comments:
Subscribe to: Posts (Atom)

Making Prompts for Profile Web Site

  Prompt: Can you create prompt to craft better draft in a given topic. Response: Sure! Could you please specify the topic for which you...