Introduction to Artificial IntelligenceDeep Learning - Tensor Flow

Janyl JumadinovaDecember 2, 2016

Credit: Google Workshop

Neural Networks

2/24

Neural Networks

3/24

Neural NetworksA fully connected NN layer

4/24

Implementation as Matrix Multiplication

5/24

Non-Linear Data Distributions

6/24

7/24

Deep Learning

I Each neuron implements a relatively simple mathematicalfunction.

I y = g(w · x + b)

I The composition of 106 − 109 such functions is powerful.

8/24

Deep Learning

I Each neuron implements a relatively simple mathematicalfunction.

I y = g(w · x + b)

I The composition of 106 − 109 such functions is powerful.

8/24

Deep Learning

Book: http://www.deeplearningbook.org/

Chapter 5

“A core idea in deep learning is that we assume that the data wasgenerated by the composition of factors or features, potentially atmultiple levels in a hierarchy.”

9/24

Results get better with:

I more data

I bigger models

I more computation

Better algorithms, new insights and improved methods help, too!

10/24

Results get better with:

I more data

I bigger models

I more computation

Better algorithms, new insights and improved methods help, too!

10/24

11/24

Adoption of Deep Learning Tools on GitHub

12/24

Tensor FlowI Operates over tensors: n-dimensional arrays

I Using a flow graph: data flow computation framework

13/24

Tensor FlowI Operates over tensors: n-dimensional arrays

I Using a flow graph: data flow computation framework

13/24

Tensor FlowI Operates over tensors: n-dimensional arrays

I Using a flow graph: data flow computation framework

13/24

Tensor Flow

I 5.7 ← Scalar

I Number, Float, etc.

14/24

Tensor Flow

15/24

Tensor Flow

16/24

Tensor Flow

I Tensors have a Shape that is described with a vector

I [1000, 256, 256, 3]

I 10000 Images

I Each Image has 256 Rows

I Each Row has 256 Pixels

I Each Pixel has 3 values (RGB)

17/24

Tensor Flow

I Tensors have a Shape that is described with a vector

I [1000, 256, 256, 3]

I 10000 Images

I Each Image has 256 Rows

I Each Row has 256 Pixels

I Each Pixel has 3 values (RGB)

17/24

Tensor Flow

Computation is a dataflow graph

18/24

Tensor Flow

Computation is a dataflow graph with tensors

19/24

Tensor Flow

Computation is a dataflow graph with state

20/24

Core TensorFlow data structures and concepts

I Graph: A TensorFlow computation, represented as a dataflowgraph:- collection of ops that may be executed together as a group.

I Operation: a graph node that performs computation on tensors

I Tensor: a handle to one of the outputs of an Operation:- provides a means of computing the value in a TensorFlowSession.

21/24

Core TensorFlow data structures and concepts

I Graph: A TensorFlow computation, represented as a dataflowgraph:- collection of ops that may be executed together as a group.

I Operation: a graph node that performs computation on tensors

I Tensor: a handle to one of the outputs of an Operation:- provides a means of computing the value in a TensorFlowSession.

21/24

Core TensorFlow data structures and concepts

I Graph: A TensorFlow computation, represented as a dataflowgraph:- collection of ops that may be executed together as a group.

I Operation: a graph node that performs computation on tensors

I Tensor: a handle to one of the outputs of an Operation:- provides a means of computing the value in a TensorFlowSession.

21/24

Tensor Flow

I Constants

I Placeholders: must be fed with data on execution.

I Variables: a modifiable tensor that lives in TensorFlow’s graphof interacting operations.

I Session: encapsulates the environment in which Operationobjects are executed, and Tensor objects are evaluated.

22/24

Tensor Flow

I Constants

I Placeholders: must be fed with data on execution.

I Variables: a modifiable tensor that lives in TensorFlow’s graphof interacting operations.

I Session: encapsulates the environment in which Operationobjects are executed, and Tensor objects are evaluated.

22/24

Tensor Flow

I Constants

I Placeholders: must be fed with data on execution.

I Variables: a modifiable tensor that lives in TensorFlow’s graphof interacting operations.

I Session: encapsulates the environment in which Operationobjects are executed, and Tensor objects are evaluated.

22/24

Tensor Flow

I Constants

I Placeholders: must be fed with data on execution.

I Variables: a modifiable tensor that lives in TensorFlow’s graphof interacting operations.

I Session: encapsulates the environment in which Operationobjects are executed, and Tensor objects are evaluated.

22/24

Tensor Flow

23/24

Tensor Flow

playground.tensorflow.org

24/24