Neural Networks with Google TensorFlow
Download as PPTX, PDF61 likes57,219 views
The document provides an overview of neural networks, particularly convolutional neural networks (CNNs) using Google TensorFlow, covering their architecture and mathematical concepts. It highlights key elements of TensorFlow, including tensors, operations, and sessions, and explains the role of dropout as a technique to prevent overfitting in neural networks. Furthermore, it discusses the application of TensorFlow in various projects at Google and introduces TensorBoard for visualizing learning processes.
Neural Networks with Google TensorFlow
- 1. Neural Networks with Google TensorFlow Darshan Patel Northeastern University
- 2. • Overview: 1) Computer Vision Tasks 2) Convolution Neural Network (CNNs) Architecture 3) CNNs using Google TensorFlow 4) Google TensorBoard Neural Networks with Google TensorFlow
- 13. • Mathematical Definition: A function derived from two given functions by integration that expresses how the shape of one is modified by the other What is Convolution?
- 14. Neural Networks
- 15. Neural Networks - Forward Pass
- 16. Neural Networks - Back Propagation Source : http://cs231n.github.io
- 17. • ConvNet architectures make the explicit assumption that the inputs are images, which allows us to encode certain properties into the architecture. • This assumption makes the forward function more efficient to implement and vastly reduces the amount of parameters in the network. How CNN/ConvNets is different?
- 18. Cont. How CNN/ConvNets is different? Source : http://cs231n.github.io/convolutional-networks
- 19. LeNet-5 1990 Yann LeCun Director of AI Research at Facebook Handwritten Digits Classification
- 21. AlexNet Architecture - ImageNet 2012
- 26. Layers in ConvNets 1. Convolution Layer 2. ReLU (Activation) Layer 3. Pooling Layer 4. Fully Connected Layer
- 43. • A ConvNet architecture is a list of Layers that transform the image volume into an output volume (e.g. holding the class scores) • There are a few distinct types of Layers (e.g. CONV/FC/RELU/POOL are by far the most popular) • Each Layer accepts an input 3D volume and transforms it to an output 3D volume through a differentiable function • Each Layer may or may not have parameters (e.g. CONV/FC do, RELU/POOL don't) ConvNets Summary
- 46. • Second generation Machine Learning system, followed by DistBelief • TensorFlow grew out of a project at Google, called Google Brain, aimed at applying various kinds of neural network machine learning to products and services across the company. • An open source software library for numerical computation using data flow graphs • Used in following projects at Google 1. DeepDream 2. RankBrain 3. Smart Reply And many more.. Google TensorFlow
- 47. Data Flow Graph • Data flow graphs describe mathematical computation with a directed graph of nodes & edges • Nodes in the graph represent mathematical operations. • Edges represent the multidimensional data arrays (tensors) communicated between them. • Edges describe the input/output relationships between nodes. • The flow of tensors through the graph is where TensorFlow gets its name.
- 48. Google TensorFlow Basic Elements • Tensor • Variable • Operation • Session • Placeholder • TensorBoard
- 49. • TensorFlow programs use a tensor data structure to represent all data • Think of a TensorFlow tensor as an n-dimensional array or list In the following example, c, d and e are symbolic Tensor Objects, where as result is a numpy array Tensor
- 50. 1. Constant Value Tensors 2. Sequences 3. Random Tensors Tensor Types
- 52. Sequence Tensors
- 53. Random Tensors
- 54. • In-memory buffers containing tensors • Initial value defines the type and shape of the variable. • They must be explicitly initialized and can be saved to disk during and after training. Variable
- 55. • An Operation is a node in a TensorFlow Graph • Takes zero or more Tensor objects as input, and produces zero or more Tensor objects as output. • Example: c = tf.matmul(a, b) Creates an Operation of type "MatMul" that takes tensors a and b as input, and produces c as output. Operation
- 56. • A class for running TensorFlow operations • InteractiveSession is a TensorFlow Session for use in interactive contexts, such as a shell and Ipython notebook. Session & Interactive Session
- 57. • A value that we'll input when we ask TensorFlow to run a computation. Placeholder
- 58. TensorBoard : Visual Learning
- 59. MNIST Dataset
- 60. MNIST Dataset
- 62. Load MNIST Data
- 63. Load MNIST Data Start a session
- 66. Convolution and Pooling Stride of one Max Pooling over 2x2 blocks Stride of two
- 67. First Convolution Layer including ReLU It will consist of convolution, followed by max pooling Filter/Patch Dimension Number of Input Channels Number of Output Channel Number of Output Channel
- 68. Second Convolution Layer including ReLU It will consist of convolution, followed by max pooling
- 69. Fully Connected Layer • Reshape the tensor from the pooling layer into a batch of vectors • Multiply by a weight matrix, add a bias, and apply a ReLU
- 70. Dropout • To reduce over fitting, we will apply dropout before the readout layer. • Dropout is an extremely effective, simple and recently introduced regularization technique by Srivastava et al. in “Dropout: A Simple Way to Prevent Neural Networks from Overfitting” that complements the other methods (L1, L2, maxnorm). Source : http://cs231n.github.io/neural-networks-2/
- 71. Dropout • We create a placeholder for the probability that a neuron's output is kept during dropout. • This allows us to turn dropout on during training, and turn it off during testing. • While training, dropout is implemented by only keeping a neuron active with some probability pp (a hyperparameter)
- 72. Readout Layer • Finally, we add a softmax layer, just like for the one layer softmax regression.
- 73. Train and Evaluate the Model Initialize All Variables Training Accuracy Testing Optimizer Loss Function
- 74. • TensorBoard operates by reading TensorFlow events files, which contain summary data that you can generate when running TensorFlow. TensorBoard
- 75. • TensorBoard operates by reading TensorFlow events files, which contain summary data that you can generate when running TensorFlow. • First, create the TensorFlow graph that we'd like to collect summary data from, and decide which nodes should be annotated with summary operation. • For example, • For MNIST digits CNNs, we'd like to record how the learning rate varies over time, and how the objective function is changing • We’d like to record distribution of gradients or weights TensorBoard
- 77. TensorBoard
- 78. TensorBoard
Editor's Notes
- #15: Regular Neural Nets don't scale well to full images.