Michael Erlihson’s Post

Our Latest episode is on the Cramer-Rao bound, specifically, Rao’s seminal paper.

🎙️ Exciting News! 🎙️ I'm thrilled to launch a podcast, "The Mathematics and Computing Rabbit Hole: Translating Real-World Challenges into Bits and Atoms." This AI-assisted podcast, created with Google's NotebookLM, aims to demystify technology and make complex concepts accessible in layman's terms. Why listen? 1) Be Inspired by AI: Experience your first AI-generated podcast and see what's possible with today's technology. 2) Get your head around complex topics in an easy going way: Dive into intriguing subjects like mathematics and computing, and understand their real-world applications. Join me as I navigate these fields, sharing my journey to simplify and apply complex ideas to real-world challenges. Whether you're a tech leader or a curious learner, this podcast offers insights into tech assisted modern problem-solving. Your Feedback Matters: Do you like it? Is it worth a second episode? Share your thoughts and suggest topics you'd like to explore next! #Podcast #AI #Mathematics #Computing #Innovation #Learning

I just finished reading "Everything Is Predictable: How Bayesian Statistics Explain Our World" by Tom Chivers. If you are interested in #machinelearning, I highly recommend adding this to your library. Bayesian techniques are used in machine learning for classification and regression problems, particularly in the development of spam filters, recommendation systems, and in Bayesian networks for probabilistic inference. While you are at it, also check out Chris Voss's podcast on the subject (links in comments).

Discover how Dr. Travis Oliphant's passion for open source led to the creation of NumPy and SciPy, revolutionizing data science and machine learning. A must-listen episode with your host Jon Krohn! Watch the episode here: https://bit.ly/sds765 Thank you to Women in Analytics (WIA) and Data Universe, for supporting this episode of SuperDataScience, enabling the show to be freely available on all major podcasting platforms and on YouTube. #datascience #numpy #scipy

🎉 Data nerds, rejoice! The 8th episode of the Data Science Rabbit Podcast has emerged from its digital warren! 🐰 Prepare for a wild ride down the rabbit hole as we tackle the age-old question: Is it easier to teach a marketer calculus or a data scientist small talk? 🤔 But wait, there's more! The illustrious Cornelius P. Snarkington graces us with his presence, offering a checklist for ethical modeling that's more detailed than your ex's stalking habits. And for dessert, a "comedy" bit about being a seasoned data scientist. Because nothing says humor like reminiscing about punch cards and FORTRAN, right? 😂 Grab your pocket protectors and tune in! Available now on Spotify and wherever else you get your auditory fix of data-driven snark. P.S. If you don't listen, our AI overlords will be very disappointed in you. Don't make the machines cry. 🤖😢 https://lnkd.in/e4wqf3xZ #DataScience #EthicalAI #DataSciencePodcast

Creating generative art with R is an incredibly abstract process that blends coding, data, mathematics, and artistic insight in a truly unique way. Experience it firsthand as Meghan Harris, MPH delves into this fascinating topic on the R for the Rest of Us podcast. Check out the episode through the audio and video links in the comments below! #Rstats #GenerativeArt #CreativeCoding #DataVisualization

🎙️ New Podcast Alert: Exploring Bayesian Workflow Dive into the influential 2020 manuscript,  Bayesian Workflow, with MetrumRG! In our latest podcast episode, VP of Statistics James Rogers leads a dynamic discussion featuring two of the paper's co-authors: 🔹 Andrew Gelman – Professor of Statistics & Political Science at Columbia University 🔹 Charles Margossian – Research Fellow at the Flatiron Institute and former MetrumRG Visiting Scientist Learn why workflow is the critical link connecting theory and practice, why it is essential to set multiple models in dialogue with each other for any given scientific problem, and why the authors see “model navigation as the next transformative step in data science." 🎧 Listen now: https://lnkd.in/gAs5rPkP and check out the open-access paper here: https://lnkd.in/d99uWfU8 As discussed in the interview, MetrumRG’s approach to workflow is embodied in our open source MeRGE ecosystem. Check out our  freely available MeRGE Expos. #OpenScience #BayesianStatistics #Pharmacometrics #MetrumRG

Congrats to our 10 winners of physical copies of Sebastian Raschka's books! I announced in Episode #767, which starred Seb, that anyone who commented on or reshared my LinkedIn post about the episode was eligible. Check out the videos for more details on how the draw is conducted and how you could get free books in the future! Today's book winners are: 1. Paul CC (ML Q&AI) 2. Swati Kabi (ML Q&AI) 3. Michael Lockhart (ML Q&AI) 4. Prajwal Srinivas (ML Q&AI) 5. Aditya Nair (ML Q&AI) 6. Ganesh Bhat (LLMs from Scratch) 7. Bilal Saleem (LLMs from Scratch) 8. Dev Brat T. (ML Q&AI) 9. Zach Jacobson (LLMs from Scratch) 10. Jonathan Bown (ML Q&AI) Many thanks to Women in Analytics (WIA), Data Universe and No Starch Press for supporting this episode of Super Data Science, enabling the show to be freely available on all major podcasting platforms as well as the video version we publish on YouTube. This draw was for Episode #767! #superdatascience #machinelearning #ai #pytorch

Sometimes, it's nice to get back to the basics and have conversations about the importance of statistics in ML/AI and how these mathematical foundations are vital to monitor algorithms over time--limiting the potential harm they may cause. I enjoyed joining Data Nerds in the OR #podcast, hosted by Bruce Ramshaw, to chat about this and other fun data topics! Listen to the full discussion here: https://lnkd.in/eTAdXFZa #AIinHealthcare #DataScience #PlatypusHealth Platypus Health

“Applying Mathematical Principles to People Analytics with Keith McNulty Part 2” from the ScienceForWork Podcast is now available! The conversation continues with Keith McNulty, Natasha Ouslis, PhD, Bilal Alperen Ergun, and Matthew Lampe, PsyD. In this episode, we dive into the intersection of mathematical principles and people analytics, exploring the practicalities and challenges of applying scientific evidence within organizations. 🔍 Here are three key takeaways from Part 2: Balance Between Science and Practicality:  - Keith emphasizes the importance of balancing scientific rigor with practical application. Starting with simple, explainable models when introducing scientific methodologies can build trust and set the foundation for more complex analyses over time. 🧩 Understanding Statistical Significance and Causality:  - A common pitfall identified is the oversimplification of statistical results. Identifying a statistically significant difference doesn’t necessarily explain why it exists. Proper interpretation and mindful communication of data are essential to avoid misleading conclusions. 📊 Patience and Communication are Crucial: - Patience for scientific processes and effective communication of results are critical for effectiveness. Regular updates and clear communication help stakeholders appreciate and understand the value of a scientific approach. 📡 🎧 Listen now Spotify: https://lnkd.in/gbEzKfPB Apple: https://lnkd.in/gYheMd4b Amazon: https://lnkd.in/gRtenzkr Thank you, Keith McNulty, for a great 2-part conversation full of evidence-based insights and practical application. To dive deeper into these topics with more evidence-based research, studies, and meta-analyses, check out our website: www.ScienceForWork.com #PeopleAnalytics #DataScience #Mathematics #EvidenceBasedManagement #ScienceForWork #MakeWorkBetter