Machine Learning

Syndicate content 5 

 

Keywords:   Jupyter Notebook, Tensorflow GPU, Keras, Deep Learning, MLP,  and HealthShare    

 

1. Purpose and Objectives

In  previous"Part I" we have set up a deep learning demo environment. In this "Part II" we will test what we could do with it.

Many people at my age had started with the classic MLP (Multi-Layer Perceptron) model. It is intuitive hence conceptually easier to start with.

So let's try a Keras "deep learning MLP" with standard demo data that everybody in AI/NN community has been using. It is a kind of so called "supervised learning". We will see how simple to run it on the Keras level.

We could later touch on its history and on why it's called "deep learning" the buzz word - what actually evolved over the recent 20 years.

1 2
0

comments

55

views

+ 1

rating

 

Keywords:  Anaconda, Jupyter Notebook, Tensorflow GPU, Deep Learning,  Python 3 and HealthShare    

1. Purpose and Objectives

This "Part I" is a quick record on how to set up a "simple" but popular deep learning demo environment step-by-step with a Python 3 binding to a HealthShare 2017.2.1 instance .  I used a Win10 laptop at hand, but the approach works the same on MacOS and Linux.

Last week it was noticed that Python overtook Java by becoming the most popular language in PYPL Index.  Tensorflow is a powerful computation engine, which is very popular in research and academic worlds too. HealthShare is a data platform that provides an unified care record of patients for care providers

1 2
0

comments

105

views

+ 3

rating

Hi Everyone!

New session recording from Global Summit 2018 is available on Developer Community YouTube Channel:

Embedded Analytics in Action

 

0 1
0

comments

21

views

0

rating

Hi Community!

Please welcome a new video on Developer Community YouTube Channel:

Alexa: Connect Me with the World of IoT

 

1 1
0

comments

100

views

+ 1

rating

Hi all. We are going to find duplicates in a dataset using Apache Spark Machine Learning algorithms.

Note: I have done the following on Ubuntu 18.04, Python 3.6.5, Zeppelin 0.8.0, Spark 2.1.1

Introduction

In previous articles we have done the following

0 1
0

comments

145

views

0

rating

Hi all.

I want to insert my dataframe into InterSystems IRIS. So, I tried to do this:

df = spark.read.load("/home/imported-openssh-key/zeppelin-0.8.0-bin-all/bin/resultData3/DF.json", format="json")
df.write.format("com.intersystems.spark").\
option("url", "IRIS://localhost:51773/DEDUPL").\
option("user", "********").option("password", "********").\
option("dbtable", "try.test1").save()

And got this error

Last answer 21 September 2018 Last comment 21 September 2018
0 1
171

views

0

rating

We’re now less than a month away from our annual conference, the InterSystems Global Summit. This year, we’ll be descending on the beautiful outskirts of San Antonio, a city worth visiting for its wonderful river walkway and its 18th century Spanish Mission, even if it hadn’t been the location of this year’s InterSystems event. Leaving the tourist guidance to the tourist guides, let’s take a closer look at what the conference has in stock for you, including a dedicated post-summit symposium on AI and ML on Wednesday October 3!

0 1
0

comments

126

views

+ 4

rating

Hi Everyone!

Very soon, almost every product and application will include artificial intelligence (AI).

On the afternoon of Wednesday, October 3, at the Global Summit 2018  in San Antonio we’re pulling together experts from InterSystems and from the front lines of the AI industry to discuss the current and future state-of-the-art for AI solutions. 

Learn more about our Post-Summit Symposium: Artificial Intelligence and Machine Learning.

Last comment 9 August 2018
0 2
308

views

+ 2

rating

The recording of Anton Umnikov's It's Machine Learning, Not Rocket Science! webinar is now available on learning.intersystems.com

In it, Anton provides a great, high-level introduction to machine learning and shows why you don't need to be a "unicorn" data scientist to start using machine learning to your advantage! 

Watch it now

0 1
0

comments

75

views

0

rating

Hi all. Today we are going to upload a ML model into IRIS Manager and test it.

Note: I have done the following on Ubuntu 18.04, Apache Zeppelin 0.8.0, Python 3.6.5.

Introduction

These days many available different tools for Data Mining enable you to develop predictive models and analyze the data you have with unprecedented ease. InterSystems IRIS Data Platform provide a stable foundation for your big data and fast data applications, providing interoperability with modern DataMining tools.

Last comment 30 July 2018
1 2
318

views

+ 5

rating

Hi all. Today we are going to use k-means algorithm on the Iris Dataset.

Note: I have done the following on Ubuntu 18.04, Apache Zeppelin 0.8.0, python 3.6.5.

Introduction

K-Means is one of the simplest unsupervised learning algorithms that solves the clustering problem. It groups all the objects in such a way that objects in the same group (group is a cluster) are more similar (in some sense) to each other than to those in other groups. For example, assume you have an image with a red ball on the green grass. K-Means will split all pixels into two clusters. The first cluster will contain the pixels of the ball, the second cluster will contain the pixels of the grass

3 2
0

comments

2446

views

+ 6

rating

Hi all. Yesterday I tried to connect Apache Spark, Apache Zeppelin, and InterSystems IRIS. During the process, I experienced troubles connecting it all together and I did not find a useful guide. So, I decided to write my own.

Introduction

What is Apache Spark and Apache Zeppelin and find out how it works together. Apache Spark is an open-source cluster-computing framework. It provides an interface for programming entire clusters with implicit data parallelism and fault tolerance. So, it is very useful when you need to work with Big Data. And Apache Zeppelin is a notebook, that provides cool UI to work with analytics and machine learning. Together, it works like this: IRIS provides data, Spark reads provided data, and in a notebook we work with the data.

Note: I have done the following on Windows 10

1 2
0

comments

402

views

+ 8

rating

With the release of InterSystems IRIS, we're also making available a nifty bit of software that allows you to get the best out of your InterSystems IRIS cluster when working with Apache Spark for data processing, machine learning and other data-heavy fun. Let's take a closer look at how we're making your life as a Data Scientist easier, as you're probably already facing tough big data challenges already, just from the influx of job offers in your inbox!

Last comment 17 May 2018
0 4
457

views

+ 2

rating

Apache Spark has rapidly become one of the most exciting technologies for big data analytics and machine learning. Spark is a general data processing engine created for use in clustered computing environments. Its heart is the Resilient Distributed Dataset (RDD) which represents a distributed, fault tolerant, collection of data that can be operated on in parallel across the nodes of a cluster. Spark is implemented using a combination of Java and Scala and so comes as a library that can run on any JVM. Spark also supports Python (PySpark) and R (SparkR) and includes libraries for SQL (SparkSQL), machine learning (MLlib), graph processing (GraphX), and stream processing (Spark Streaming).

0 4
1607

views

+ 11

rating

Last week, we announced the InterSystems IRIS Data Platform, our new and comprehensive platform for all your data endeavours, whether transactional, analytics or both. We've included many of the features our customers know and loved from Caché and Ensemble, but in this article we'll shed a little more light on one of the new capabilities of the platform: SQL Sharding, a powerful new feature in our scalability story.

Last comment 31 January 2018
0 8
836

views

+ 12

rating

Hi Guys,

Can you please guide me on how to develop the machine learning concepts like as Chatbots, voice recognition, etc...

If any lead would be appreciate. 

Thanks in Advance.

Thanks and Regards,

Arun Kumar Durairaj. 

Last answer 24 November 2017 Last comment 24 November 2017
0 3
208

views

0

rating

Several years ago everyone got mad about BigData – nobody knew when smallish data will become BIGDATA, but all knows that it’s trendy and the way to go. Time passed, BigData is not a buzz anymore (most of us missed the moment when Gartner has removed BigData term from their 2016 buzzword 2016 curve http://www.kdnuggets.com/2015/08/gartner-2015-hype-cycle-big-data-is-out-machine-learning-is-in.html), so it’s probably a good time to look back and realize what it is (what it was)…

When it becomes “BigData”?

Let’s start from the beginning: what is the moment when “not so big data” becomes BigData? Here was the answer in 2015 from David Kanter[1], one of most respected, well known x86 architecture specialist

Last comment 28 March 2017
0 3
1143

views

+ 6

rating