Stephen Odaibo, MD, MS(Math), MS(Comp. Sci.)’s Post

I was so lucky to learn support vector machines from the ground up. It is indeed the hallmark of classical machine learning and foundational to so many of the models we see and know today.

SVM's are definitely one of the more interesting supervised learning models. Maximizing the margin while minimizing classification error using hinge loss.

Mathematics is the compass for navigating the vast seas of machine learning, guiding us towards intelligent solutions. In my latest video, we unravel the essential mathematics underpinning machine learning, beginning with key matrix concepts such as rank, determinants, and their roles in defining singularity and inverses. We illustrate how matrices embody machine learning problems, emphasizing the specialized optimization of CPUs and GPUs for these tasks. The video further delves into vector transformations, including scaling, rotation, eigenvectors, eigenvalues, and their significance in techniques like PCA. We explore the vital function of derivatives in identifying critical points and apply these insights to minimize loss functions in machine learning, comparing analytical and numerical methods like gradient descent and Newton-Raphson. This comprehensive guide is aimed at enhancing your understanding of the mathematical groundwork essential for advanced machine learning applications and interview preparation. Video Link: youtu.be/oMY2uKjx_Zc  Channel Link: youtube.com/@datatrek #datatrek #datascience #machinelearning #statistics #deeplearning #ai

Mathematics is the compass for navigating the vast seas of machine learning, guiding us towards intelligent solutions. In my latest video, we unravel the essential mathematics underpinning machine learning, beginning with key matrix concepts such as rank, determinants, and their roles in defining singularity and inverses. We illustrate how matrices embody machine learning problems, emphasizing the specialized optimization of CPUs and GPUs for these tasks. The video further delves into vector transformations, including scaling, rotation, eigenvectors, eigenvalues, and their significance in techniques like PCA. We explore the vital function of derivatives in identifying critical points and apply these insights to minimize loss functions in machine learning, comparing analytical and numerical methods like gradient descent and Newton-Raphson. This comprehensive guide is aimed at enhancing your understanding of the mathematical groundwork essential for advanced machine learning applications and interview preparation. Video Link: youtu.be/oMY2uKjx_Zc  Channel Link: youtube.com/@datatrek #datatrek #datascience #machinelearning #statistics #deeplearning #ai

Mathematics is the compass for navigating the vast seas of machine learning, guiding us towards intelligent solutions. In my latest video, we unravel the essential mathematics underpinning machine learning, beginning with key matrix concepts such as rank, determinants, and their roles in defining singularity and inverses. We illustrate how matrices embody machine learning problems, emphasizing the specialized optimization of CPUs and GPUs for these tasks. The video further delves into vector transformations, including scaling, rotation, eigenvectors, eigenvalues, and their significance in techniques like PCA. We explore the vital function of derivatives in identifying critical points and apply these insights to minimize loss functions in machine learning, comparing analytical and numerical methods like gradient descent and Newton-Raphson. This comprehensive guide is aimed at enhancing your understanding of the mathematical groundwork essential for advanced machine learning applications and interview preparation. Video Link: youtu.be/oMY2uKjx_Zc  Channel Link: youtube.com/@datatrek #datatrek #datascience #machinelearning #statistics #deeplearning #ai

Here is the official implementation for my accepted work at ETRA 2024. The code includes computer vision, dimensionality reduction, and image segmentation techniques to crucially close the domain gap between synthetic and real datasets. Not only does this work tackle the Sim2Real problem in the eye-tracking context, but it also is really helpful for practical, real-life deep learning in general when one tries to learn a deep learning model in cross-domain datasets. Check out the code here: https://lnkd.in/eCYq6dWq Don't forget to give a star to the repository if you like it!

Central to efficient Machine Learning predictions is the meticulous calibration of mathematical functions to suit our dataset. Specifically, we endeavor to optimize the coefficients of a polynomial function to achieve the utmost alignment with data points. Employing advanced optimization techniques like Mean Absolute Error (MAE) or Mean Squared Error (MSE), the computer iteratively refines the model until it converges, a computationally demanding endeavor that mandates the utilization of robust GPU resources. Upon further investigation, I've come to realize that the standard form of the function employed in Machine Learning is f(x) = b + W1x^1 + W2x^2... Wnx^n. This is what finally helped me understand this subject, especially after delving into additional research. Despite my relatively short tenure in ML, this newfound clarity has been transformative. No math, no machine learning. #genai #ml #machinelearning #generativeai #deeplearning

Mathematics is the compass for navigating the vast seas of machine learning, guiding us towards intelligent solutions. In my latest video, we unravel the essential mathematics underpinning machine learning, beginning with key matrix concepts such as rank, determinants, and their roles in defining singularity and inverses. We illustrate how matrices embody machine learning problems, emphasizing the specialized optimization of CPUs and GPUs for these tasks. The video further delves into vector transformations, including scaling, rotation, eigenvectors, eigenvalues, and their significance in techniques like PCA. We explore the vital function of derivatives in identifying critical points and apply these insights to minimize loss functions in machine learning, comparing analytical and numerical methods like gradient descent and Newton-Raphson. This comprehensive guide is aimed at enhancing your understanding of the mathematical groundwork essential for advanced machine learning applications and interview preparation. Video Link: youtu.be/oMY2uKjx_Zc  Channel Link: youtube.com/@datatrek #datatrek #datascience #machinelearning #statistics #deeplearning #ai

Mathematics is the compass for navigating the vast seas of machine learning, guiding us towards intelligent solutions. In my latest video, we unravel the essential mathematics underpinning machine learning, beginning with key matrix concepts such as rank, determinants, and their roles in defining singularity and inverses. We illustrate how matrices embody machine learning problems, emphasizing the specialized optimization of CPUs and GPUs for these tasks. The video further delves into vector transformations, including scaling, rotation, eigenvectors, eigenvalues, and their significance in techniques like PCA. We explore the vital function of derivatives in identifying critical points and apply these insights to minimize loss functions in machine learning, comparing analytical and numerical methods like gradient descent and Newton-Raphson. This comprehensive guide is aimed at enhancing your understanding of the mathematical groundwork essential for advanced machine learning applications and interview preparation. Video Link: youtu.be/oMY2uKjx_Zc  Channel Link: youtube.com/@datatrek #datatrek #datascience #machinelearning #statistics #deeplearning #ai

Seen at #spielitho! Yuansheng Ma was at SPIE this week introducing a method that employs a deep learning model, built with GPU, to extract contours from a variety of SEM images through his paper "Machine learning based SEM contour extraction accelerated by GPU for etch modeling application" Not at SPIE? Watch for our wrap up blog coming soon covering our week here!