Scribd Logo
Upload

Welcome to Scribd!

  • 68 views

    Introduction To Deep Learning

    Uploaded by

    Jerzo Sikne
    The document is an introduction to deep learning in Python. It discusses how deep learning can better capture interactions in data compared to linear regression. Neural networks with multiple hidden layers are able to model complex relationships. Activation functions are applied to node inputs to introduce non-linearity. Deeper networks with more hidden layers can learn increasingly complex representations of the data.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Introduction To Deep Learning

    Uploaded by

    Jerzo Sikne
    68 views79 pages
    The document is an introduction to deep learning in Python. It discusses how deep learning can better capture interactions in data compared to linear regression. Neural networks with multiple hidden layers are able to model complex relationships. Activation functions are applied to node inputs to introduce non-linearity. Deeper networks with more hidden layers can learn increasingly complex representations of the data.

    Original Description:

    Deep learning

    Original Title

    Introduction to deep learning

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document is an introduction to deep learning in Python. It discusses how deep learning can better capture interactions in data compared to linear regression. Neural networks with multiple hidden layers are able to model complex relationships. Activation functions are applied to node inputs to introduce non-linearity. Deeper networks with more hidden layers can learn increasingly complex representations of the data.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    68 views79 pages

    Introduction To Deep Learning

    Uploaded by

    Jerzo Sikne
    The document is an introduction to deep learning in Python. It discusses how deep learning can better capture interactions in data compared to linear regression. Neural networks with multiple hidden layers are able to model complex relationships. Activation functions are applied to node inputs to introduce non-linearity. Deeper networks with more hidden layers can learn increasingly complex representations of the data.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 79

    Introduction to deep

    learning
    INTRODUCTION TO DEEP LEARNING IN PYTHON

    Dan Becker
    Data Scientist and contributor to Keras
    and TensorFlow libraries
    Imagine you work for a bank
    You need to predict how many transactions each customer
    will make next year

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Example as seen by linear regression

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Interactions
    Neural networks account for interactions really well

    Deep learning uses especially powerful neural networks


    Text

    Images

    Videos

    Audio

    Source code

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Course structure
    First two chapters focus on conceptual knowledge
    Debug and tune deep learning models on conventional
    prediction problems

    Lay the foundation for progressing towards modern


    applications

    This will pay o in the third and fourth chapters

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Build and tune deep learning models using keras
    import numpy as np
    from tensorflow.keras.layers import Dense
    from tensorflow.keras.models import Sequential
    predictors = np.loadtxt('predictors_data.csv', delimiter=',')
    n_cols = predictors.shape[1]
    model = Sequential()

    model.add(Dense(100, activation='relu', input_shape = (n_cols,)))


    model.add(Dense(100, activation='relu'))
    model.add(Dense(1))

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Deep learning models capture interactions

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Deep learning models capture interactions

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Deep learning models capture interactions

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Interactions in neural network

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Interactions in neural network

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Interactions in neural network

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Interactions in neural network

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Interactions in neural network

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Let's practice!
    INTRODUCTION TO DEEP LEARNING IN PYTHON
    Forward
    propagation
    INTRODUCTION TO DEEP LEARNING IN PYTHON

    Dan Becker
    Data Scientist and contributor to Keras
    and TensorFlow libraries
    Bank transactions example
    Make predictions based on:
    Number of children

    Number of existing accounts

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation
    Multiply - add process

    Dot product

    Forward propagation for one data point at a time

    Output is the prediction for that data point

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation code
    import numpy as np
    input_data = np.array([2, 3])
    weights = {'node_0': np.array([1, 1]),
    'node_1': np.array([-1, 1]),
    'output': np.array([2, -1])}
    node_0_value = (input_data * weights['node_0']).sum()
    node_1_value = (input_data * weights['node_1']).sum()

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Forward propagation code
    hidden_layer_values = np.array([node_0_value, node_1_value])
    print(hidden_layer_values)

    [5, 1]

    output = (hidden_layer_values * weights['output']).sum()


    print(output)

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Let's practice!
    INTRODUCTION TO DEEP LEARNING IN PYTHON
    Activation functions
    INTRODUCTION TO DEEP LEARNING IN PYTHON

    Dan Becker
    Data Scientist and contributor to Keras
    and TensorFlow libraries
    Linear vs. non-linear Functions

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Activation functions
    Applied to node inputs to produce node output

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Improving our neural network

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Activation functions

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    ReLU (Rectified Linear Activation)

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Activation functions
    import numpy as np
    input_data = np.array([-1, 2])
    weights = {'node_0': np.array([3, 3]),
    'node_1': np.array([1, 5]),
    'output': np.array([2, -1])}
    node_0_input = (input_data * weights['node_0']).sum()
    node_0_output = np.tanh(node_0_input)
    node_1_input = (input_data * weights['node_1']).sum()
    node_1_output = np.tanh(node_1_input)
    hidden_layer_outputs = np.array([node_0_output, node_1_output])
    output = (hidden_layer_output * weights['output']).sum()

    print(output)

    1.2382242525694254

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Let's practice!
    INTRODUCTION TO DEEP LEARNING IN PYTHON
    Deeper networks
    INTRODUCTION TO DEEP LEARNING IN PYTHON

    Dan Becker
    Data Scientist and contributor to Keras
    and TensorFlow libraries
    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Multiple hidden layers

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Representation learning
    Deep networks internally build representations of pa erns in
    the data

    Partially replace the need for feature engineering

    Subsequent layers build increasingly sophisticated


    representations of raw data

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Representation learning

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Deep learning
    Modeler doesn't need to specify the interactions

    When you train the model, the neural network gets weights
    that nd the relevant pa erns to make be er predictions

    INTRODUCTION TO DEEP LEARNING IN PYTHON


    Let's practice!
    INTRODUCTION TO DEEP LEARNING IN PYTHON

    You might also like