Best of Math — June 2024

  1. 1
    Article
    Avatar of freecodecampfreeCodeCamp·2y

    Practical Guide to Linear Algebra in Data Science and AI

    Linear algebra is a practical tool that can be used to solve real-world problems in data science and AI. It is applied across various industries, and understanding its core concepts is essential for working with machine learning, deep learning, computer vision, and generative AI. A linear algebra roadmap for 2024 is provided to guide your learning journey, and there are numerous resources available to help you master linear algebra.

  2. 2
    Article
    Avatar of medium_jsMedium·2y

    Linear Algebra Concepts Every Data Scientist Should Know

    Linear algebra is fundamental in transforming theoretical data science models into practical solutions. It is crucial for data representation, dimensionality reduction, optimization, feature engineering, and similarity measures. Concepts such as vectors, vector spaces, matrices, and operations like dot products and matrix multiplication are key foundational topics. Understanding the basis, rank, determinants, eigenvectors, and eigenvalues are vital for advanced applications in data science and machine learning.

  3. 3
    Video
    Avatar of fireshipFireship·2y

    JAX in 100 Seconds

    Jax is an accelerated linear algebra library that allows for high-performance array computing and automatic differentiation. It enforces constraints like immutable arrays and pure functions. Jax can run on accelerated hardware like GPUs and TPUs.

  4. 4
    Article
    Avatar of hnHacker News·2y

    Tetris Font

    This post introduces a unique Tetris-inspired font where each letter and digit is constructed using Tetris pieces. The design process involved hand design aided by BurrTools software to ensure pieces fit correctly. It includes a puzzle font where letters' positions represent their drop sequence, improving the challenge. The post also touches on the NP-complete nature of Tetris and acknowledges contributions from collaborators at BRIDGES 2017.

  5. 5
    Article
    Avatar of medium_jsMedium·2y

    The Math Behind KAN — Kolmogorov-Arnold Networks

    Discover the math behind Kolmogorov-Arnold Networks (KANs), a revolutionary alternative to Multi-Layer Perceptrons (MLPs) in the world of AI and neural networks. Learn about the limitations of MLPs, how KANs leverage the Kolmogorov-Arnold representation theorem, and the advantages of using KANs in terms of accuracy, interpretability, and scalability.

See all Math archives