kaggie.com

Category: Machine Learning

  • “Digits” Classification

    —

    by

    Josh
    in ,

    ^above is my classification approach trained for 10 epochs ^the same network trained for 200 epochs, >98% accuracy ^a much simpler CNN for 50 epochs…. hmm The classification of handwritten digits stands as a foundational problem in machine learning and computer vision, serving as a benchmark for developing and evaluating various algorithmic approaches. Its significance…

  • Meta-Analysis of Posts

    —

    by

    Josh
    in ,

    Reading URLs from test_urls.txt…Fetching https://www.kaggie.com/facts-about-monkeys/…Fetching https://www.kaggie.com/frontoremporal-dementia/…Fetching https://www.kaggie.com/the-basal-lamina/…Fetching https://www.kaggie.com/beyond-the-bond-unveiling-molecular-architecture-with-the-nuclear-overhauser-effect/…— Text Analysis Example — Analyzing frequency of ‘spin’…www_kaggie_com_facts: 0www_kaggie_com_front: 0www_kaggie_com_the_b: 0www_kaggie_com_beyon: 335Saved ‘spin_comparison.png’ — TF-IDF Analysis — Top 20 TF-IDF words for www_kaggie_com_facts:[(‘monkeys’, 0.0449000708758831), (‘their’, 0.01359560340642929), (‘monkey’, 0.012195081450045109), (‘baboons’, 0.008314828388392925), (‘macaques’, 0.007760506588965654), (‘like’, 0.006942435633391142), (‘world’, 0.006368696689605713), (‘some’, 0.006014880258589983), (‘species’, 0.005681438371539116), (‘primates’, 0.0055432189255952835), (‘them’, 0.005244405008852482), (‘social’, 0.005206826608628035), (‘old’,…

  • ARC – find the rule!

    —

    by

    Josh
    in

    Can you beat a computer? https://arcprize.org/play

  • Vision Transformer Code

    —

    by

    Josh
    in

    see: https://www.kaggie.com/a-deep-dive-into-vision-transformers-and-clip/ (note, this is only 1 epoch. Certainly a better result would occur with more training.) Code explanation by Gemini: This code implements a Vision Transformer (ViT) to classify handwritten digits from the MNIST dataset. Instead of using traditional Convolutional Neural Networks (CNNs) that look at pixels through sliding windows, this model treats an…

  • Network Effects, Philosophy, and the Fabric of Our Shared Reality

    —

    by

    Josh
    in , , ,

    Table of Contents The Invisible Handshake: Understanding Network Effects and Their Philosophical Roots (It used “the intricate dance” in the first sentence! silly…) Unpacking the Invisible Handshake: Defining Network Effects and Their Manifestations The intricate dance of connection and value that underpins so much of the modern digital landscape is often guided by an unseen…

  • AI Agents in Healthcare

    —

    by

    Josh
    in , ,

    (note: these references are hallucinations. This particular method needs refinement! ) 1. Introduction: The Dawn of Intelligent Automation in Healthcare The landscape of modern healthcare is undergoing a profound transformation, driven by unprecedented advancements in artificial intelligence (AI). Among the most promising frontiers within AI research are AI agents – autonomous entities capable of perceiving…

  • New Machine Learning Methods – Multimodal Imaging and Medicine

    —

    by

    Josh
    in ,

    (note: annoyingly this method did not keep accurate references…) The confluence of new machine learning (ML) methods, multimodal imaging, and medicine marks a pivotal advancement in healthcare. This synergistic integration promises to significantly enhance diagnostic precision, facilitate personalized treatment strategies, and ultimately improve patient outcomes. While traditional medical imaging techniques, such as MRI, CT, PET,…

  • New Machine Learning Methods in Multimodal AI

    —

    by

    Josh
    in ,

    Multimodal machine learning (ML) represents a rapidly advancing frontier in artificial intelligence, focusing on the development of systems capable of processing, interpreting, and integrating information from diverse sensory modalities. These modalities include, but are not limited to, text, images, audio, video, and sensor data. By mimicking human cognitive processes that naturally combine various sensory inputs,…

  • Machine Learning in Medical Imaging

    —

    by

    Josh
    in , , , ,

    Table of Contents Chapter 1: The Promise of AI in Medical Imaging: An Introduction 1.1 The Evolution of Medical Imaging: From Analogue to Digital and Beyond The journey of medical imaging is a fascinating narrative of scientific discovery, technological innovation, and an unwavering commitment to improving patient care. From the serendipitous observation of X-rays to…

  • A Deep Dive into Vision Transformers and CLIP

    —

    by

    Josh
    in ,

    Chapter 1: From Pixels to Patches: The Rise of Vision Transformers (ViTs) 1.1 The Convolutional Era and its Limitations: A Historical Context for ViTs (Discuss the strengths and weaknesses of CNNs, their architectural biases, and their struggle with long-range dependencies which ViTs aim to solve) The story of Vision Transformers (ViTs) is best understood by…

  • The Self-Evolving Codebase: Autonomous Software Development Lifecycles and Frameworks

    —

    by

    Josh
    in , ,

    (note – these “books” aren’t interesting until the later chapters, e.g., like the 7th… I need to tweak my generation of them. For declaration, I regularly use autonomous SDLC methods but have different views on how they should be structured – but that’s for another time.) Chapter 1: The Autonomous SDLC Revolution: Understanding the Drivers…

  • Seeing is Believing: A Comprehensive Guide to Vision Machine Learning

    —

    by

    Josh
    in , ,

    Chapter 1: The Vision Machine: An Introduction to Computer Vision and Machine Learning 1.1 A Historical Journey: From Biological Vision to Artificial Perception The human visual system is a marvel of biological engineering, a testament to millions of years of evolution. To truly understand the ambition and challenges of computer vision, it’s essential to appreciate…