TensorFlow in 1 Day Make your own Neural Network

TensorFlow in 1 Day: Make your own Neural Network......Page 2
Chapter 3: What is TensorFlow?......Page 3
Chapter 7: Tensorflow on AWS......Page 4
Chapter 11: Pandas......Page 5
Chapter 15: Linear Classifier in TensorFlow......Page 6
Chapter 19: Autoencoder with TensorFlow......Page 7
Chapter 20: RNN(Recurrent Neural Network) TensorFlow......Page 8
What is Deep learning?......Page 9
Deep learning Process......Page 11
Classification of Neural Networks......Page 13
Types of Deep Learning Networks......Page 14
Feed-forward neural networks......Page 15
Recurrent neural networks (RNNs)......Page 16
Convolutional neural networks (CNN)......Page 18
Reinforcement Learning......Page 19
Applications/ Examples of deep learning applications......Page 20
Why is Deep Learning Important?......Page 22
Limitations of deep learning......Page 23
Summary......Page 24
What is AI?......Page 25
What is ML?......Page 27
What is Deep Learning?......Page 28
Machine Learning Process......Page 29
Deep Learning Process......Page 31
Automate Feature Extraction using DL......Page 32
Difference between Machine Learning and Deep Learning......Page 34
When to use ML or DL?......Page 35
Summary......Page 36
What is TensorFlow?......Page 37
History of TensorFlow......Page 39
TensorFlow Architecture......Page 40
Where can Tensorflow run?......Page 41
Introduction to Components of TensorFlow......Page 42
Why is TensorFlow popular?......Page 44
List of Prominent Algorithms supported by TensorFlow......Page 45
Simple TensorFlow Example......Page 46
Options to Load Data into TensorFlow......Page 49
Create Tensorflow pipeline......Page 51
Summary......Page 52
Chapter 4: Comparison of Deep Learning Libraries......Page 55
8 Best Deep learning Libraries /Framework......Page 56
MICROSOFT COGNITIVE TOOLKIT(CNTK)......Page 58
TenserFlow Vs Theano Vs Torch Vs Keras Vs infer.net Vs CNTK Vs MXNet Vs Caffe: Key Differences......Page 60
Google Cloud ML......Page 61
AWS SageMaker......Page 62
Azure Machine Learning Studio......Page 63
IBM Watson ML......Page 64
Verdict:......Page 65
Chapter 5: How to Download and Install TensorFlow Windows and Mac......Page 66
TensorFlow Versions......Page 67
Install Anaconda......Page 69
Create .yml file to install Tensorflow and dependencies......Page 70
Launch Jupyter Notebook......Page 83
Jupyter with the main conda environment......Page 88
What is Jupyter Notebook?......Page 89
Jupyter Notebook App......Page 90
How to use Jupyter......Page 91
Summary......Page 101
Chapter 7: Tensorflow on AWS......Page 102
PART 1: Set up a key pair......Page 103
PART 2: Set up a security group......Page 106
Launch your instance (Windows users)......Page 115
Part 4: Install Docker......Page 122
Part 5: Install Jupyter......Page 123
Troubleshooting......Page 127
What is a Tensor?......Page 128
Representation of a Tensor......Page 129
Types of Tensor......Page 131
Create a tensor of n-dimension......Page 132
Shape of tensor......Page 135
Type of data......Page 137
Some Useful TensorFlow operators......Page 138
Variables......Page 140
Placeholder......Page 142
Session......Page 143
Graph......Page 147
Summary......Page 150
What is TensorBoard......Page 152
Summary:......Page 164
What is NumPy?......Page 165
Why use NumPy?......Page 166
Create a NumPy Array......Page 167
Mathematical Operations on an Array......Page 169
3 Dimension Array......Page 170
np.zeros and np.ones......Page 172
Reshape and Flatten Data......Page 174
hstack and vstack......Page 175
Asarray......Page 176
Arrange......Page 178
LogSpace......Page 179
Indexing and slicing......Page 180
Statistical function......Page 181
Matrix Multiplication......Page 182
Determinant......Page 183
Summary......Page 184
What is Pandas?......Page 188
Why use Pandas?......Page 189
How to install Pandas?......Page 190
What is a data frame?......Page 191
What is a Series?......Page 192
Range Data......Page 193
Inspecting data......Page 194
Slice data......Page 196
Drop a column......Page 198
Drop_duplicates......Page 199
Import CSV......Page 200
Groupby......Page 202
Summary......Page 206
What is Scikit-learn?......Page 207
Download and Install scikit-learn......Page 208
Machine learning with scikit-learn......Page 210
Step 1) Import the data......Page 211
Step 2) Create the train/test set......Page 218
Step 3) Build the pipeline......Page 219
Step 4) Using our pipeline in a grid search......Page 222
XGBoost Model with scikit-learn......Page 225
Create DNN with MLPClassifier in scikit-learn......Page 230
Data Preparation......Page 231
Summary......Page 242
Linear regression......Page 244
How to train a linear regression model......Page 245
How to train a Linear Regression with TensorFlow......Page 252
Pandas......Page 254
Numpy Solution......Page 263
Tensorflow solution......Page 267
Chapter 14: Linear Regression Case Study......Page 276
Summary statistics......Page 279
Facets Overview......Page 283
Facets Deep Dive......Page 284
Install Facet......Page 285
Overview......Page 288
Graph......Page 291
Facets Deep Dive......Page 297
Preparation data......Page 299
Basic regression:Benchmark......Page 300
Improve the model: Interaction term......Page 304
What is Linear Classifier?......Page 309
How Binary classifier works?......Page 310
Accuracy......Page 313
Precision and Sensitivity......Page 314
Linear Classifier with TensorFlow......Page 316
Step 1) Import the data......Page 317
Step 2) Data Conversion......Page 319
Step 3) Train the Classifier......Page 323
Step 4) Improve the model......Page 327
Bucketization and interaction......Page 333
Step 5) Hyperparameter:Lasso & Ridge......Page 337
Summary......Page 341
Chapter 16: Kernel Methods......Page 343
Why do you need Kernel Methods?......Page 344
What is a Kernel in machine learning?......Page 350
Type of Kernel Methods......Page 352
Train Gaussian Kernel classifier with TensorFlow......Page 353
What is Artificial Neural Network?......Page 366
Neural Network Architecture......Page 369
Optimizer......Page 372
Network size......Page 373
Dropout......Page 374
Example Neural Network in TensorFlow......Page 375
Step 1) Import the data......Page 378
Step 2) Transform the data......Page 379
Step 4) Build the model......Page 380
Step 6) Improve the model......Page 381
Summary......Page 383
What is Convolutional Neural Network?......Page 384
Architecture of a Convolutional Neural Network......Page 385
Components of Convnets......Page 388
Step 1: Upload Dataset......Page 397
Step 2: Input layer......Page 400
Step 6: Dense layer......Page 401
Step 7: Logit Layer......Page 402
What is an Autoencoder?......Page 409
How does Autoencoder work?......Page 410
Stacked Autoencoder Example......Page 412
Build an Autoencoder with TensorFlow......Page 413
Image preprocessing......Page 414
Set Dataset Estimator......Page 417
Build the network......Page 419
What do we need an RNN?......Page 428
What is RNN?......Page 429
Limitations of RNN......Page 434
RNN in time series......Page 435
Build an RNN to predict Time Series in TensorFlow......Page 438
DID YOU ENJOY THE BOOK?......Page 447
Learn R Programming in 1 Day: Complete Guide for Beginners......Page 448