https://software.intel.com/en-us/articles/distributed-training-of-deep-networks-on-amazon-web-services-aws
Models
Platforms
Tools
Products
Algorithms
IDEs
Languages
of the 7%, 60% ~ " classical machine learning " and 40% ~ "deep learning."
7% of server sales in 2016 were for AI but it is
the "fastest-growing data center workload."
fyi: 97% (of the classical machine learning) used Intel Xeon processors to handle the computations
Cortex-M Processors
M0 (basic): low cost, power & area
M3, M4, M33: middle tier apps
M7: embedded applications
M23, M33: security
*M4, M7, M33 process DSP algorithms such as sensor fusion, motor control and power management
Text
Not quite ML ready
R to merge with M series
https://devblogs.nvidia.com/parallelforall/digits-deep-learning-gpu-training-system/
https://devblogs.nvidia.com/parallelforall/digits-deep-learning-gpu-training-system/
image and video classification
computer vision
speech recognition
natural language processing
audio recognition
et al
incorporate GPU acceleration
http://deeplearning.net/software/theano/tutorial/
ARM stressed that the number of chips ...shipped...will be simpler ARM chips (low-power Cortex-R and Cortext-M designs, like those used in Fitbits)
HOWEVER
https://www.theverge.com/2017/3/21/14998100/arm-new-dynamiq-microarchitecture-ai-chip-design
can be used to to programme the FPGA
e.g., convert hardware design language (HDL) files into a configuration bitstream
http://web.mit.edu/6.111/www/s2004/NEWKIT/ise.shtml
For IoT gateways
edit, save, simulate, synthesise SystemVerilog, Verilog, VHDL and other HDLs from your web browser
predict a binary outcome
one of two possible classes, true or false
algorithm such as logistic regression
"Is this email spam or not spam?"
"Will the customer buy this product?"
"Is this product a book or a farm animal?"
"Is this review written by a customer or a robot?"
allows you to generate predictions for multiple classes
predict one of more than two outcomes
algorithm such as multinomial logistic regression
"Is this product a book, movie, or clothing?"
"Is this movie a romantic comedy, documentary, or thriller?"
"Which category of products is most interesting to this customer?"
predict a numeric value
algorithm such as linear regression
"What will the temperature be in Seattle tomorrow?"
"For this product, how many units will sell?"
"What price will this house sell for?"
http://mccormickml.com/2013/08/15/radial-basis-function-network-rbfn-tutorial/
a.) What makes some tools and products better, faster or cheaper than others?
b.) Are regression and classification the most important problems for tools and products to solve?
c.) Which other tools and products are good for machine learning engineering and/or data science?
https://www.tensorflow.org/get_started/tflearn
https://www.tensorflow.org/get_started/tflearn
Input your training datasources
historical data (csv)
prediction file (csv)
Enter instructions for data transformations
Training parameters to control the learning algorithm
https://www.tensorflow.org/get_started/tflearn
create two datasources,
one for training the model and
one for evaluating the model
https://www.tensorflow.org/get_started/tflearn
Maximum model size
Maximum number of passes over training data
Shuffle type
Regularization type
Regularization amount
https://www.tensorflow.org/get_started/tflearn
evaluate the predictive quality of the ML model
https://www.tensorflow.org/get_started/tflearn
evaluate the predictive quality of the ML model
https://www.tensorflow.org/get_started/tflearn
Review the ML Model's Predictive Performance
Set a Score Threshold
https://www.tensorflow.org/get_started/tflearn
Review the ML Model's Predictive Performance
https://www.tensorflow.org/get_started/tflearn
Input training datasource
Name of the data attribute that contains the target to be predicted
Required data transformation instructions
Training parameters to control the learning algorithm
https://www.tensorflow.org/get_started/tflearn
Input training datasource
Name of the data attribute that contains the target to be predicted
Required data transformation instructions
Training parameters to control the learning algorithm
https://www.tensorflow.org/get_started/tflearn
Input your training datasources
historical data (csv)
prediction file (csv)
Enter instructions for data transformations
Training parameters to control the learning algorithm
https://www.tensorflow.org/get_started/tflearn
insert reference
insert reference
insert reference
insert reference
TensorFlow’s high-level machine learning API (tf.contrib.learn) makes it easy to configure, train, and evaluate a variety of machine learning models. In this tutorial, you’ll use tf.contrib.learn to construct a neural network classifier and train it on the Iris data set to predict flower species based on sepal/petal geometry.
https://www.tensorflow.org/get_started/tflearn
You'll write code to perform the following five steps:
NOTE: TensorFlow should e installed onto your machine before getting started with this tutorial.
https://people.orie.cornell.edu/davidr/or474/deveaux.pdf
see multilayer feedforward network
https://people.orie.cornell.edu/davidr/or474/deveaux.pdf
https://people.orie.cornell.edu/davidr/or474/deveaux.pdf