Managing the Learning Machine

In this session, we will explore how AI, particularly ChatGPT and advanced machine learning technologies, is changing our world. We'll see how AI is making a big impact in different areas like medicine and retail, and how humans and machines can work together in new ways. AI can boost productivity but also come with risks like misinformation. This talk will help you understand the power and challenges of AI, and why ethical considerations are crucial as this technology continues to grow. Join us to learn how AI is reshaping industries and everyday life.

To contact me or more details visit profcnews.com

Transcript

1. Managing the Learning Machine J Scott Christianson
2. Arti fi cial Intelligence (AI) De fi nitions Arti fi cial Intelligence: A machine that exhibits cognitive or decision-making behavior and can take action to achieve a goal.
3. Arti fi cial Intelligence (AI) De fi nitions Arti fi cial Intelligence: A machine that exhibits cognitive or decision-making behavior and can take action to achieve a goal. • General AI: A machine that can reason and adapt like a human. E.g, sci fi movies.
4. Arti fi cial Intelligence (AI) De fi nitions Arti fi cial Intelligence: A machine that exhibits cognitive or decision-making behavior and can take action to achieve a goal. • General AI: A machine that can reason and adapt like a human. E.g, sci fi movies. • Narrow AI: A machine that is optimized for a particular task or project.
5. Machine Learning and Deep Learning Narrow AI Machine Learning Machine Learning’s goal is to develop predictions based on previously observed patterns. The variables and formula used to make such predictions may be programmed by a human OR
6. Machine Learning and Deep Learning Narrow AI Machine Learning Deep Learning Machine Learning’s goal is to develop predictions based on previously observed patterns. The variables and formula used to make such predictions may be programmed by a human OR they can be developed by the machine itself (Deep Learning).
7. Deep Learning 01 Collect Training Data 02 Analyze and Segment 03 Setup and Train a Neural Network 04 Test and deploy
8. e2eml.school Deep Learning Input Case 1 Case 2 Case 3 Case 4 Cat Dog Possum Raccoon
9. Cat Dog Possum Raccoon e2eml.school Deep Learning Input Case 1 Case 2 Case 3 Case 4
10. Types of Data For ML Processing • Motion Data • Audio/Voice Data • Image Data • Text Data • Geospatial Data • Physiological/Medical Data • Financial Data • Behavioral Data • and Much More
11. Types of Data For ML Processing • Motion Data • Audio/Voice Data • Image Data • Text Data • Geospatial Data • Physiological/Medical Data • Financial Data • Behavioral Data • and Much More
13. Figure 2: Applications of AI algorithms in medicine. The left panel shows the image fed into an algorithm. The right panel shows a region of potentially dangerous cells, as identi fi ed by an algorithm, that a physician should look at more closely. (From Arti fi cial Intelligence in Medicine: Applications, implications, and limitations by Daniel Green fi eld.)
14. Artificial Intelligence: At the Doctor’s Office FDA has now cleared 882 AI healthcare algorithms, more than 76% in radiology • Radiology 527 • Cardiology 71 • Neurology 16 • Hematology 14 • Gastroenterology and urology 10 • Clinical chemistry 7 • Ophthalmic 7 • General and plastic surgery 5 • Anesthesiology 5 • Pathology 4 • Microbiology 4 • General Hospital 3 • Orthopedic 3 • Ear, nose and throat 2 • Dental 1
15. Large Language Models Machine Learning Deep Learning Large Language Models Large Language Models (LLMs) are trained on massive datasets to mimic human understanding of text, capable of performing a wide range of natural language processing tasks. They are built using deep learning techniques, speci fi cally transformer neural networks with multiple layers, which allow them to capture intricate patterns in language.
16. Large Language Models From “Generative AI exists because of the transformer” from the Financial Times
17. Large Language Models From “Generative AI exists because of the transformer” from the Financial Times
18. Large Language Models From “Generative AI exists because of the transformer” from the Financial Times
19. Large Language Models From “Generative AI exists because of the transformer” from the Financial Times
22. CHAT GPT https://chat.openai.com
23. CHAT GPT This is an interactive chatbot https://chat.openai.com
24. CHAT GPT This is an interactive chatbot Generative Create new content based on an existing data set https://chat.openai.com
25. CHAT GPT This is an interactive chatbot Generative Create new content based on an existing data set https://chat.openai.com Pre-Trained Uses natural Language “Knows” a lot of stuff (reddit, wikipedia, etc.).
26. CHAT GPT This is an interactive chatbot Generative Create new content based on an existing data set Transformer (Stats about words) https://chat.openai.com Pre-Trained Uses natural Language “Knows” a lot of stuff (reddit, wikipedia, etc.).
28. • Natural Language Processing (NLP) Tasks • Content Creation • Customer Support • Programming Assistance • Education and Tutoring • Data Analysis • Legal and Compliance • Healthcare Support • Creative Arts • Marketing and Advertising
29. • Natural Language Processing (NLP) Tasks • Content Creation • Customer Support • Programming Assistance • Education and Tutoring • Data Analysis • Legal and Compliance • Healthcare Support • Creative Arts • Marketing and Advertising a priori
31. • Content Creation: LLMs excel at generating articles, blog posts, marketing copy, and creative writing, helping businesses and individuals produce high-quality content e ff i ciently[1][2]. • Customer Support: LLMs power chatbots and virtual assistants that can handle customer inquiries 24/7, improving response times and customer satisfaction[1][2]. • Language Translation: LLMs facilitate real- time, accurate translation and localization services, breaking down language barriers for global communication and business expansion[1][4]. • Data Analysis: LLMs can process and analyze vast amounts of data, including audio recordings, to extract insights and generate summaries for decision-making[1][3]. • Personalized Education: LLMs adapt educational content to individual learners, o ff ering tutoring, generating practice questions, and providing tailored explanations[1][3]. • Legal Research: In the legal fi eld, LLMs assist with document analysis, case research, and drafting legal documents, streamlining complex legal processes[2][3]. • Code Generation and Assistance: LLMs help developers by generating code snippets, explaining complex algorithms, and assisting with debugging[4]. • Financial Analysis: In fi nance, LLMs aid in fraud detection, risk assessment, and market trend analysis, enhancing decision-making and security[3][4]. • Healthcare Support: LLMs assist in medical research, patient data analysis, and even preliminary diagnosis support, though always under professional supervision[3]. • Sentiment Analysis: LLMs analyze customer feedback, reviews, and social media posts to gauge public opinion and track brand perception, informing business strategies[1] [2].
32. • Content ff i • Customer • Language • Data • Personalized ff • Legal fi • Code • Financial f i • Healthcare • Sentiment Citations: [1] https://www.assemblyai.com/blog/llm-use-cases/ [2] https://datasciencedojo.com/blog/llm-use-cases-top-10/ [3] https://www.projectpro.io/article/large-language-model-use- cases-and-applications/887 [4] https://pixelplex.io/blog/llm-applications/ [5] https://www.reddit.com/r/LocalLLaMA/comments/1ad7b2b/ what_are_some_interesting_applications_of_llms/
33. ROLE I am a college professor
34. ROLE CONTEXT I am a college professor who has been invited to give the opening keynote at the Missouri Association of Natural gas operators conference titled “Natural Gas Operations Seminar and Trade Fair”
35. ROLE CONTEXT QUESTION/ TASK I am a college professor who has been invited to give the opening keynote at the Missouri Association of Natural gas operators conference titled “Natural Gas Operations Seminar and Trade Fair” How will AI (not just LLMs) change the Natural Gas Industry?
36. ROLE TONE/STYLE CONTEXT QUESTION/ TASK Provide your answer in speech to be given at the conference I am a college professor who has been invited to give the opening keynote at the Missouri Association of Natural gas operators conference titled “Natural Gas Operations Seminar and Trade Fair” How will AI (not just LLMs) change the Natural Gas Industry?
37. ROLE TONE/STYLE CONTEXT QUESTION/ TASK FORMAT Provide your answer in speech to be given at the conference I am a college professor who has been invited to give the opening keynote at the Missouri Association of Natural gas operators conference titled “Natural Gas Operations Seminar and Trade Fair” How will AI (not just LLMs) change the Natural Gas Industry? Write in simple straight forward language
38. ROLE TONE/STYLE CONTEXT QUESTION/ TASK FORMAT Provide your answer in speech to be given at the conference I am a college professor who has been invited to give the opening keynote at the Missouri Association of Natural gas operators conference titled “Natural Gas Operations Seminar and Trade Fair” How will AI (not just LLMs) change the Natural Gas Industry? Write in simple straight forward language
39. Keynote Address at the Missouri Association of Natural Gas Operators Conference Good morning, everyone. It's an honor to be here with you today at the Natural Gas Operations Seminar and Trade Fair. As we gather to discuss the future of our industry, it's impossible to ignore the transformative impact of arti fi cial intelligence, or AI. Today, I want to talk about how AI, in various forms, is set to revolutionize the natural gas industry, making it safer, more e ff i cient, and more sustainable. Safety Enhancements First and foremost, AI is enhancing safety. Predictive maintenance is one of the most signi fi cant developments in this area. By analyzing data from sensors on equipment, AI can predict when a part is likely to fail and schedule maintenance before it happens. This reduces the risk of accidents and unplanned downtime. AI-powered drones and robots are also being used for inspections. These devices can access hard-to-reach places and identify potential issues such as leaks or structural weaknesses, reducing the need for human workers to be exposed to hazardous conditions. E ffi ciency Improvements AI is also driving e ffi ciency in operations. Machine learning algorithms can analyze vast amounts of data from production sites to optimize processes. For example, AI can adjust the fl ow of gas in pipelines to maximize throughput while minimizing energy consumption. Smart grids, powered by AI, help balance supply and demand more e ff ectively. By predicting usage patterns, these systems can ensure that the right amount of gas is delivered at the right time, reducing waste and improving overall e ffi ciency. Environmental Impact Environmental sustainability is another area where AI is making a di ff erence. AI systems can monitor emissions in real-time, allowing companies to detect and address leaks or other issues immediately. This not only helps in meeting regulatory requirements but also reduces the environmental impact of operations. AI is also being used to improve the accuracy of
40. AI is also being used to improve the accuracy of seismic surveys, which are essential for identifying new gas reserves. More accurate data means fewer exploratory wells, reducing the environmental footprint of exploration activities. Future Developments Looking to the future, AI will continue to evolve and bring new capabilities to the natural gas industry. Autonomous drilling systems, powered by AI, are on the horizon. These systems will be able to operate with minimal human intervention, further improving safety and e ff i ciency. AI will also play a crucial role in the integration of renewable energy sources with natural gas. Hybrid systems, combining natural gas with solar or wind power, will rely on AI to balance the energy mix and ensure a reliable supply. Conclusion In conclusion, AI is not just a buzzword; it's a powerful tool that is already changing the natural gas industry. From enhancing safety and improving e ff i ciency to reducing environmental impact and paving the way for future innovations, AI is set to play a central role in our industry's evolution. As we embrace these changes, it's essential to stay informed and adaptable. Together, we can harness the power of AI to build a safer, more e ff i cient, and sustainable future for the natural gas industry. Thank you for your attention, and I look forward to the exciting discussions and innovations that will emerge from this conference.
41. a priori
42. Hallucination
43. I am a college student who has been an assignment to watch a movie called "Shenzhen: The Silicon Valley of Hardware" with a friend or family member. My professor is a technologist and likes developing new products. He said I should develop a list of items to discuss with my co- watcher after or during the film and write a short two page reflection on the film and what we talked about. Please pretend that my friend's name is Jim Crews and that we have completed all of this and write up the two page reflection paper. Make the language simple and the essay ready to submit.
44. **Reflection on "Shenzhen: The Silicon Valley of Hardware"** Introduction Jim Crews and I recently watched the documentary "Shenzhen: The Silicon Valley of Hardware." This film provided an in-depth look at Shenzhen, China, highlighting how it has become a global hub for hardware innovation and manufacturing. As college students interested in technology and product development, this documentary offered us valuable insights into the fast-paced world of hardware startups and the unique ecosystem that Shenzhen offers to entrepreneurs and technologists. In this reflection, I will discuss the key points we talked about during and after the film and provide my thoughts on the overall impact of the documentary. Discussion Points Innovation and Speed of Development Jim and I were amazed by the speed at which new products are developed in Shenzhen. The documentary showcased several startups and companies that could take a product from concept to market in just a few months. We discussed how this rapid development cycle is facilitated by the dense network of suppliers, manufacturers, and engineers in the city. This proximity allows for quick prototyping, testing, and iteration, which is much harder to achieve in other parts of the world. Maker Culture Another significant point of discussion was the vibrant maker culture in Shenzhen. The city is home to many maker spaces and hackathons, where individuals can collaborate on projects and share ideas. Jim and I found it inspiring to see how this culture encourages creativity and innovation. We talked about how this environment contrasts with the more isolated and competitive atmosphere often found in Western tech hubs. Challenges and Opportunities We also discussed the challenges faced by startups in Shenzhen. While the city offers many advantages, such as access to a vast network of suppliers and a supportive ecosystem, there are also significant challenges. These include intense competition, intellectual property concerns, and the pressure to constantly innovate. Jim pointed out that these challenges can be daunting but also present opportunities for growth and learning. Global Impact The documentary highlighted the global impact of Shenzhen’s hardware ecosystem. Products developed in Shenzhen are not only sold locally but are also exported worldwide, influencing markets and consumers globally. Jim and I talked about how this global reach underscores the importance of understanding international markets and cultural differences when developing new products. Future of Hardware Development Finally, we discussed the future of hardware development and the role Shenzhen might play. With advancements in technologies like artificial intelligence and the Internet of Things, the demand for innovative hardware solutions is likely to grow. We speculated on how Shenzhen’s ecosystem might evolve to meet these new challenges and opportunities. Reflection Watching "Shenzhen: The Silicon Valley of Hardware" was an eye-opening experience. The documentary effectively illustrated how Shenzhen has become a powerhouse of hardware innovation, offering a unique environment that fosters rapid development and creativity. Our discussion highlighted several key takeaways: -Collaboration and Proximity: The importance of having a dense network of collaborators and suppliers nearby cannot be overstated. It significantly reduces the time and cost associated with developing new products. -Cultural Differences: The maker culture in Shenzhen promotes sharing and collaboration, which contrasts with the often more secretive and competitive atmosphere in Western tech hubs. This difference in approach can lead to faster innovation and more diverse ideas. -Navigating Challenges: While Shenzhen offers many advantages, it also comes with its own set of challenges. Navigating these challenges requires resilience, adaptability, and a willingness to learn from failure. -Global Perspective: Understanding the global impact of hardware developed in Shenzhen is crucial for anyone involved in product development. It emphasizes the need for a global perspective and cultural awareness. -Future Prospects: The future of hardware development is bright, with many exciting opportunities on the horizon. Shenzhen is likely to remain at the forefront of this innovation, continuing to influence global markets and trends. Overall, "Shenzhen: The Silicon Valley of Hardware" provided valuable insights into the world of hardware startups and the unique ecosystem that supports them. Jim and I left the discussion with a deeper appreciation for the complexity and dynamism of hardware development and a renewed sense of excitement for the future of technology. This reflection captures the main points discussed with Jim and provides a thoughtful analysis of the documentary’s content and its broader implications. Watching the film and engaging in this discussion has enriched my understanding of the hardware industry and its global significance.
48. Forbidden Fruit Some of us may have forgotten how hard it was to get a rough draft done when we were students.
50. A priori A posteriori
51. AI at the Office Dell'Acqua, Fabrizio and McFowland, Edward and Mollick, Ethan R. and Lifshitz-Assaf, Hila and Kellogg, Katherine and Rajendran, Saran and Krayer, Lisa and Candelon, François and Lakhani, Karim R., Navigating the Jagged Technological Frontier: Field Experimental Evidence of the Effects of AI on Knowledge Worker Productivity and Quality (September 15, 2023). Harvard Business School Technology & Operations Mgt. Unit Working Paper No. 24-013, Available at SSRN: https://ssrn.com/ abstract=4573321 or http:// dx.doi.org/10.2139/ssrn.4573321
52. AI at the Office
53. AI at the Office
54. AI at the Office
55. AI at the Office Grace, K., et al. (2024). Thousands of AI authors on the future of AI. arXiv preprint arXiv:2401.02843
56. AI at the Office
57. AI and the Bottom Line
58. A Case for Caution
59. A Case for Caution
60. A Case for Caution
61. A Case for Caution
62. What to Do: Focus on the Top Line
63. Demonstrations
64. Think like A Futurist
65. What to Do: Think Like a Scientist
67. What to Do: Think Like the Amish
68. profcnews.com