TensorFlow - Revision history

Unknown user: /* Flags */

2025-05-11T20:12:04Z

Flags

2017-10-28T01:45:07Z

MNIST

← Older revision		Revision as of 01:45, 28 October 2017
Line 19:		Line 19:
	===MNIST===		===MNIST===

	[[TensorFlow/MNIST]] - a basic ~~illustration of a~~ convolutional ~~neural~~ network to do handwritten digit classification		[[TensorFlow/MNIST]] - illustrating a basic convolutional network to do handwritten digit classification

			[[TensorFlow/MNIST2]] - a more, uh, convoluted example of how to do convolutional neural networks (lower-level, manual initialization and layer assembly, etc.)

	===Adversarial Neural Networks===		===Adversarial Neural Networks===

2017-10-27T10:05:51Z

TensorFlow Models Repository

← Older revision		Revision as of 10:05, 27 October 2017
Line 16:		Line 16:

	Writeups of models from https://github.com/tensorflow/models		Writeups of models from https://github.com/tensorflow/models

			===MNIST===

			[[TensorFlow/MNIST]] - a basic illustration of a convolutional neural network to do handwritten digit classification

	===Adversarial Neural Networks===		===Adversarial Neural Networks===

2017-10-27T03:04:20Z

Example TensorFlow Networks

← Older revision		Revision as of 03:04, 27 October 2017
Line 13:		Line 13:
	This section contains a list of TensorFlow networks that have writeups on the wiki.		This section contains a list of TensorFlow networks that have writeups on the wiki.

	==Adversarial Neural Networks==		==TensorFlow Models Repository==

			Writeups of models from https://github.com/tensorflow/models

			===Adversarial Neural Networks===

	[[TensorFlow/Adversarial Crypto]] - a triplet adversarial neural network configuration (encoder/decoder/eavesdropper networks corresponding to Alice/Bob/Eve).		[[TensorFlow/Adversarial Crypto]] - a triplet adversarial neural network configuration (encoder/decoder/eavesdropper networks corresponding to Alice/Bob/Eve).

	==Research Networks==		===Research Networks===

	[[TensorFlow/Differential Privacy]] - a research neural network configuration intended to help protect the privacy of users in crowdsourced data sets. Main challenge is in minimizing a non-convex loss function.		[[TensorFlow/Differential Privacy]] - a research neural network configuration intended to help protect the privacy of users in crowdsourced data sets. Main challenge is in minimizing a non-convex loss function.


	=Usage and Components=		=Usage and Components=

2017-10-27T01:00:58Z

Usage and Components

← Older revision		Revision as of 01:00, 27 October 2017
Line 8:		Line 8:

	Engineering TensorFlow Models: [[GCDEC/Engineering_Tensorflow/Notes]]		Engineering TensorFlow Models: [[GCDEC/Engineering_Tensorflow/Notes]]

			=Example TensorFlow Networks=

			This section contains a list of TensorFlow networks that have writeups on the wiki.

			==Adversarial Neural Networks==

			[[TensorFlow/Adversarial Crypto]] - a triplet adversarial neural network configuration (encoder/decoder/eavesdropper networks corresponding to Alice/Bob/Eve).

			==Research Networks==

			[[TensorFlow/Differential Privacy]] - a research neural network configuration intended to help protect the privacy of users in crowdsourced data sets. Main challenge is in minimizing a non-convex loss function.


	=Usage and Components=		=Usage and Components=

2017-10-26T17:37:36Z

Usage and Components

← Older revision		Revision as of 17:37, 26 October 2017
Line 14:		Line 14:

	[[TensorFlow/Command Line Args]] - notes on using command line arguments in TensorFlow models		[[TensorFlow/Command Line Args]] - notes on using command line arguments in TensorFlow models


			==Projector==

			The embedding projector site is a page that uses (?) TensorFlow to create lower-dimensional visualizations from higher-dimensional data. There are several visualization options, including tSNE and PCA.

			Link: http://projector.tensorflow.org/

	==The Influence of Google Technologies==		==The Influence of Google Technologies==

2017-10-26T17:31:55Z

Other Repositories

@@ Line 56: / Line 56: @@
 ** both linear and deep models
 ** wide and deep network
 ===Other Repositories===

2017-10-26T05:20:34Z

Usage and Components

← Older revision		Revision as of 05:20, 26 October 2017
Line 14:		Line 14:

	[[TensorFlow/Command Line Args]] - notes on using command line arguments in TensorFlow models		[[TensorFlow/Command Line Args]] - notes on using command line arguments in TensorFlow models

			==The Influence of Google Technologies==

			An interesting blog post that highlights the influence of Google Technologies on TensorFlow: http://planspace.org/20170313-tensorflow_use_of_google_technologies/

			This includes:
			* gflags
			* apputils (now abseil)
			* bazel
			* protobuf
			* grpc
			* gemmlowp
			* gfile

	=Github=		=Github=

2017-10-26T05:05:16Z

Other Repositories

← Older revision		Revision as of 05:05, 26 October 2017
Line 45:		Line 45:

	===Other Repositories===		===Other Repositories===

			* https://github.com/pdsmith1223/rntn - recurrent neural networks and recursive neural tensor networks

	* https://github.com/ajschumacher/mapreduce_with_tensorflow - an unusual use of TensorFlow to perform MapReduce computations		* https://github.com/ajschumacher/mapreduce_with_tensorflow - an unusual use of TensorFlow to perform MapReduce computations

2017-10-26T04:42:10Z

Official Repositories

← Older revision		Revision as of 04:42, 26 October 2017
Line 35:		Line 35:
	** contains sequential buildup of a simple tensorflow example into a more complex tensorflow example in courses/machine_learning/tensorflow		** contains sequential buildup of a simple tensorflow example into a more complex tensorflow example in courses/machine_learning/tensorflow
	** contains example bundled app for training/predictions using Cloud ML Engine in courses/machine_learning/cloudmle		** contains example bundled app for training/predictions using Cloud ML Engine in courses/machine_learning/cloudmle

			* https://github.com/GoogleCloudPlatform/cloudml-samples - examples that demonstrate how to use Cloud ML Engine; this demonstrates multiple techniques:
			** training a Keras model using Cloud ML Engine
			** using "canned" TensorFlow estimator
			** using custom TensorFlow estimator
			** using low-level TensorFlow API
			** both linear and deep models
			** wide and deep network

	===Other Repositories===		===Other Repositories===