🖥️
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
  • Complex problems can be solved dividing them in little computation units (neurons) in a network
  • ImageNet contest (2012, when everything started)
  • Training a neural network is not easy
  1. Basic concepts on Generative AI
  2. Deep Learning

Neural networks

It is said that 'men' have just 1 neuron, if so, I understand a lot, since not many interesting problems can be solved with just 1 neuron.

PreviousArtificial neuronNextSome traditional neural network architectures

Last updated 2 years ago

Complex problems can be solved dividing them in little computation units (neurons) in a network

ImageNet contest (2012, when everything started)

  • 14 million images with 20000 hand-annotated categories (such as ‘balloon’, ‘strawberry’ and so on)

  • Objective: to minimize the error using several IA strategies

Training a neural network is not easy

Don't worry, this is not the objective of this course, but believe me, it is something compulsory if you want to do deeper into this field.