Terence Mills’ Post

How to Improve Graphs to Empower Your Machine-Learning Model’s Performance #AI #AIio #BigData #ML #NLU #Futureofwork http://ow.ly/yIxi30sBOr4

How to Improve Graphs to Empower Your Machine-Learning Model’s Performance #AI #AIio #BigData #ML #NLU #Futureofwork http://ow.ly/6K7e30sCzOa

How to Improve Graphs to Empower Your Machine-Learning Model’s Performance #AI #AIio #BigData #ML #NLU #Futureofwork http://ow.ly/yIxi30sBOr4

𝗖𝗮𝘂𝘀𝗮𝗹 𝗥𝗲𝗽𝗿𝗲𝘀𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴: 𝗧𝗵𝗲 𝗦𝗽𝗮𝗿𝗸 𝗼𝗳 𝗚𝗲𝗻𝗲𝗿𝗮𝗹 𝗔𝗜 ⚡️ The human ability to go beyond mere memorization & explore the complex web of underlying relationships underscores a profound cognitive skill: understanding the "why" behind the "what," and applying it effortlessly across domains. 🧠 Consider children's innate ability of learning how to navigate stairs: they don't need discrete lessons for each variation of a staircase. Rather, through exploration, they discover the fundamental principle of staircases - the abstract mechanism. 👶🏽🏃🏽♂️ In recent years, the dominance of deep learning, particularly in generative AI, has been undeniable. It seamlessly generates images & text across a spectrum of domains without explicit Causal Understanding. However, in their paper, the authors Jonathan Richens and Tom Everitt found that Causal Reasoning is essential for being able to generalize across different tasks: "... any agent capable of adapting to a sufficiently large number of distributional shifts must inherently possess a learned Causal Model of the data generation process," underscoring the central role of Causal Discovery in promoting robustness. 🤖📚 So, yes, Causal AI is emerging as a crucial element in general AI and AI robustness. If you want to get the details - check out their paper. If you want to know, how to best take advantage of Causal AI in your specific domain - get in touch! Don't just imitate - start understanding deeply. 😉🔍 #causalAI #causality #causaldiscovery

Making Bayesian Optimization Algorithm Simple for Practical Applications via #TowardsAI → https://bit.ly/3ScyjF1

Become an expert on aiXplain’s no-code AI platform and SDK with our #aiXpertTrainingCourse 🤓 In this tutorial, learn to transform your linguistic corpora into structured datasets with aiXplain, enhancing your AI's understanding and performance. Don't forget to subscribe to our YouTube channel for more. 👉 https://lnkd.in/gHCmvZwn #aiXplain #DataScience #Corpus #AI #MachineLearning #LearnAI #AIplatform #AItools

Just finished the course “Introduction to Artificial Intelligence”!  I found the statistical analysis approaches really very interesting: https://lnkd.in/eeU3gGmq 

Interesting article from Marco Peixeiro -- "would I use Time-LLM in a forecasting project? Probably not." But be sure to read the article! Well done. To me, layering in an LLM-component to time series is dicey. The uses of auto-ml for time series are very prone to failure (esp. with complex data patterns, causal impacts, etc.). If an algorithm doesn't do well with what to the human eye is trend + seasonality + shock or two, it will really crash and burn on anything more complicated. So, proceed with caution. https://lnkd.in/e4um-hmg

Why is dimensionality reduction crucial in machine learning? Explore Farzad Mahmoodi Nobar's tutorial on PCA, where he breaks down the concept with hands-on examples and shows you how it helps in areas like NLP and image processing. #MachineLearning #PCA

I completed Brian Fung's crash course on the Basics of Artificial Intelligence from OpenClinTech. The short format (30 minutes) is great for an introduction!