🖥️
The new revolution of Generative AI models
  • Introduction
  • Basic concepts on Generative AI
    • Computational creativity
    • Intelligence? Creativity?
    • Artificial Intelligence
    • Machine Learning
    • Deep Learning
      • What makes a cat a cat?
      • Artificial neuron
      • Neural networks
      • Some traditional neural network architectures
      • Discriminative AI vs. Generative AI
    • Generative AI
    • NLP: Natural Language Processing
      • Language models
        • Word embeddings
        • LLMs (Large Language Models)
      • Transformers
      • GPT models
        • chatGPT
    • Image generation
      • Autoencoders
      • GANs
      • Stable Diffusion model
    • This has just started...
  • Main Generative AI tools
    • Pre-trained models
    • Chatbots, search engines and LLMs
      • Whisper for automatic speech recognition
    • Coding
    • Arts and graphics
      • Stable Diffusion Web UI for image generation (among other tools)
      • StableDiffusion for generating animations between prompts
      • Topic-driven image generation with DreamBooth
        • Lensa app
      • Point-E
      • NeRF & DreamFusion
    • Writing
    • Research
    • Video
    • Music
      • Jukebox
  • Can we develop new solutions?
    • Summarizing and translating videos from YouTube
    • Converting a YouTube video to an article, caption included
    • Creating and illustrating a story from a storyline
Powered by GitBook
On this page
  • From an input image of a cat, what vector of features can you get that could help you in the training process of a model?
  • Let's try to remove the human from the feature engineering process
  1. Basic concepts on Generative AI
  2. Deep Learning

What makes a cat a cat?

If you don't know the answer, ask to a 3-year-old child, they can help you, but then try to 'program' it

PreviousDeep LearningNextArtificial neuron

Last updated 2 years ago

From an input image of a cat, what vector of features can you get that could help you in the training process of a model?

  • Image segmentation, border detection

  • Points of interest, gradients

  • Basic shapes detection

  • Fast Fourier transformation and work in frequency domain

  • etc.

This has been the work of thousands of researchers for many years, being able to find some clever, and sometime very specific, techniques to get some characteristics from images (or other inputs) or features in order to train ML models.

Let's try to remove the human from the feature engineering process

What makes a cat a cat? From an array of pixels what can we do?
With deep learning, the objective is to train from 'raw' data, and let the neural network to decide what feature to pay attention to