Deep Learning for dilettantes

overview

• What is Machine Learning

• What are Neural Networks

• Deep Learning

• Deep Learning for Art

• Convolutional Neural Networks

• Software you can use

• Convolutional Neural Networks for Art

MachinE

Learning

http://www.cs.princeton.edu/courses/archive/spr08/cos511/scribe_notes/0204.pdf

http://www.cs.princeton.edu/courses/archive/spr08/cos511/scribe_notes/0204.pdf

Neural networks

http://cs231n.github.io/neural-networks-1/

http://cs231n.github.io/neural-networks-1/

class Neuron(object):
  # ... 
  def forward(inputs):
    """ assume inputs and weights are 1-D numpy arrays and bias is a number """
    cell_body_sum = np.sum(inputs * self.weights) + self.bias
    firing_rate = 1.0 / (1.0 + math.exp(-cell_body_sum)) # sigmoid activation function
    return firing_rate

Neural networks FOR art

Wekinator

CONVOLUTIONAL Neural networks

https://openi.nlm.nih.gov/detailedresult.php?img=PMC3612699_fpsyg-04-00124-g001&req=4

Kernel Convolution

2016:

Things get Weird

https://github.com/Newmu/dcgan_code

Smile Vector

@radiodario