deep learning - taoualiw/My-Knowledge-Base GitHub Wiki

Deep Learning

Deep Learning :

  • is a part of machine learning (there are supervised and unsupervised methods) that is done using artificial neural networks, such that the networks used have more than one hidden layer.
  • A hidden layer is a layer not responsible for input or output. (The term ‘hidden’ for non-I/O layers was historically inspired by Hidden Markov Models (HMMs); you could also call them ‘middle’ or ‘internal’ layers.)
  • artificial neural network with multiple hidden layers ( RNN CNN ANN DCN)
  • TensorFlow, Theano
  • Convolutions are the basic building block for deep learning models in computer vision (and many other applications). Imgur

Artificial Neural Networks (ANNs):

Computer Vision Datasets and Models:

  • DataSets and tools
  • Models
    • 2012 AlexNet, 8 convolutional layers
    • 2014 VGG network had 19
    • 2014 Inception or GoogleNet had 22 layers
    • 2015 Residual Network Model
      • ResNet-50 had 50 layers
      • ResNet 152 had 152 layers.

Building Blocks :

Python:

References

Home | About MKB | Artificial Intelligence|Data Science | Computer Science | Mathematics | Productivity | Misc.

⚠️ **GitHub.com Fallback** ⚠️