Building a Chatbot with TensorFlow and Keras

Blog on All Things Cloud Foundry

Building a Chatbot with TensorFlow and Keras

Sophie Turol

building-an-answerbot-with-keras-and-tensorflow-v11-icon

Digital assistants built with machine learning solutions are gaining their momentum. At TensorBeat 2017, one of the sessions covered how to deliver an answer bot with Keras and TensorFlow, what tools may help to address the issues, as well as tips on training a model and improving prediction results.

(more…)

1 Comment

TensorFlow in Finance: Discussing Predictive Analytics and Budget Planning

Sophie Turol

tensorflow-in-finance-fireside-chat-tensorbeat-2017

Though practical usage of TensorFlow within finance is still in its germ phase, the scenarios are already quite a few. The fireside chat at TensorBeat 2017 discussed how the world of finance can drive value and improve customer experience from employing TensorFlow-based solutions.

(more…)

1 Comment

Deep Q-Networks and Practical Reinforcement Learning with TensorFlow

Sophie Turol

reinforcement-learning-with-tensorflow-icon

This blog post highlights things-to-know while enabling reinforcement learning with TensorFlow, as discussed at one of the sessions at TensorBeat 2017. You will find out what toolkit simplifies the work done within an environment, how to handle pitfalls of distributed learning, boost performance across multiple environments, etc.

(more…)

1 Comment

ML Toolkit for TensorFlow: Out-of-the-Box Algorithms to Boost Training Data by 50x

Sophie Turol

tensorflow-dev-summit-2017-distributed-implementations-v15

At TensorFlow Dev Summit 2017, Google’s Ashish Agarwal introduced a TensorFlow-based toolkit of machine learning algorithms. The toolkit provides out-of-the-box packed solutions to enable researchers and developers to create high-level custom model architectures.

(more…)

3 Comments

Optical Character Recognition Using One-Shot Learning, RNN, and TensorFlow

Sophie Turol

one-shot-attention-mechanism-reccurent-neural-networks-icon-v333

Optical character recognition (OCR) drives the conversion of typed, handwritten, or printed symbols into machine-encoded text. However, the OCR process brings the need to eliminate possible errors, while extracting only valuable data from ever-growing amount of it.

At the recent TensorFlow meetup, the attendees learnt how employing the one-shot attention mechanism for token extraction in Keras using TensorFlow as a back end can help out. In addition, the meetup discussed how to enable multilingual neural machine translation with TensorFlow.

(more…)

2 Comments

Performance Comparison of Ruby Frameworks, App Servers, Template Engines, and ORMs (2016)

Eugene Melnikov

performance-ruby-rails-sinatra-rack

The Ruby ecosystem is constantly evolving. There have been many changes in the engineering world since our comparison of Ruby frameworks in 2014. During the two years, we received a few requests from fellow engineers asking for an updated benchmark. So, here is the 2016 edition with more things tested.

(more…)

24 Comments

Automating Customer Interactions with IBM Watson Conversation and Bluemix

Ilya Drabenia

ibm-bluemix-watson-conversation-service

Virtual agents and chatbots can significantly optimize the operations of customer service departments. Trained to answer questions frequently asked by end users, they help organizations to automate a variety of customer interactions, engaging team members only in complex situations.

In this post, we explain how to work with the Watson Conversation service in Bluemix for creating chatbots.

(more…)

1 Comment

Using Predix UI Components: Page Layout and Login

Nick Herman

using-predix-ui-components-page-layout-login-v1

Predix provides several UI components that help you to build web apps faster and easier. The components are implemented with Polymer, a lightweight library built on top of WebComponents, and can be integrated with other Predix services, such as Time Series.

In this post, we explain the basics of using Predix UI, with focus on page layout requirements and the px-login component.

(more…)

1 Comment

Using Spark Streaming, Apache Kafka, and Object Storage for Stream Processing on Bluemix

Ilya Drabenia

stream-processing-apache-spark-kafka-on-ibm-bluemix

One of the key points in the Industrial Internet is stream data processing. Equipment fault monitoring, predictive maintenance, or real-time diagnostics are only a few of the possible use cases. Some of the services provided by IBM Bluemix enable you to significantly speed up the implementation of such use cases. With Bluemix, you are not required to deploy and configure Hadoop, Apache Kafka, or other big data tools. It allows you to launch service instances in a few clicks.

In this article, we explain how to integrate and use the most popular open-source tools for stream processing. We explore IBM Message Hub (for collecting streams), the Apache Spark service (for processing events), and IBM Object Storage (for storing results).

(more…)

2 Comments

Using Predix Analytics Services from a Node.js App

Nick Herman

ge-predix-analytics-services-v1

Predix Analytics is a set of services that enable developers to use analytics solutions implemented by data scientists from their own apps. In this post, we explain how to get started with the three services required for running Predix analytics: Analytics Catalog, Analytics Runtime, and Analytics User Interface.

With the provided instructions, you will be able to set up the services and call the Univariate Anomaly Detection analytic service from a Node.js application.

(more…)

1 Comment

Next Page »

Benchmarks and Research

Subscribe to new posts

Get new posts right in your inbox!