Artificial Intelligence

Artificial intelligence can be applied to disparate solution spaces to deliver disruptive technologies.


Related code patterns

Build an iOS game powered by Core ML and Watson Visual Recognition

Use Watson Visual Recognition and Core ML to create a Kitura-based iOS game that has a user search for a predetermined list of objects.

Determine target audience and run marketing campaigns

Pattern demonstrates the methodology to determine target audience and run marketing campaigns using Watson Studio and Watson Campaign Automation.

Detect, track, and count cars in a video

Use automatic labeling to create a model from a video, then use the model to annotate a video.

Develop a web-based mobile health app that uses machine learning

Deploy and use a web-based health app on your smartphone using Watson services on IBM Cloud and IBM Watson Studio.

Classify ICD-10 data with Watson

A simple web app shows how Watson's Natural Language Classifier (NLC) can classify ICD-10 code.

Create an app to get stock information, prices, and sentiment

Use IBM Watson Discovery, CloudantDB, Node.js, and Alpha Vantage to create a web app to monitor sentiment, price, and news for individually listed stocks.

Optimize your visual recognition classification

Build training and prediction apps with Java, Watson IoT Platform, Node-RED, and Watson Visual Recognition service.

Create an augmented reality application with facial detection

Create an app that combines ARKit with Watson Visual Recognition and a Cloudant database to give you a complete augmented reality experience.

Analyze SMS messages with Watson Knowledge Studio

Build a custom model to better categorize SMS message content using Watson Knowledge Studio and Watson Natural Language Understanding.

Recycle with Watson

Create an iOS phone application that uses a Watson Visual Recognition custom classifier to sort waste into three categories (landfill, recycling, or compost).

Get customer insights from product reviews

Walk through a working example of a web application that queries and manipulates data from the Watson Discovery Service. Use Watson Knowledge Studio to enhance the data enrichments, and then use the app's UI components as a starting point for developing your own Watson Discovery Service applications.

Generate restaurant reviews using deep learning

Train a deep learning language model in a notebook using Keras and Tensorflow.

Deploy and use a multi-framework deep learning platform on Kubernetes

Deploy and consume a deep learning platform on Kubernetes, offering TensorFlow, Caffe, PyTorch etc. as a service.

Deploy a Core ML model with Watson Visual Recognition

With Core ML, developers can integrate a trained machine learning model into an application. Watson Visual Recognition now supports exporting trained Core ML models. This code pattern shows you how to create a Core ML model using Watson Visual Recognition, which is then bundled into an application.

Integrate Watson AI into Salesforce apps

Learn how to use the Watson Salesforce SDK to make calls to Watson Visual Recognition, Watson Discovery, and Watson Tone Analyzer APIs.

Analyze open medical datasets to gain insights

Use this code pattern as a beginning guide to run through various machine learning classifiers and compare the outputs with evaluating measures.

Create an app to perform intelligent searches on data

Walk through a working example of a web application that queries and manipulates data from the Watson Discovery Service. This web app contains multiple UI components that you can use as a starting point for developing your own Watson Discovery Service applications.

Locate and count items with object detection

This code pattern demonstrates how to use PowerAI Vision Object Detection to detect and label objects within an image.

Classify vehicle damage images

Create a mobile app that takes a picture of vehicle damage and sends it to an insurance company to identify and classify the problem.

Mine insights from software development artifacts

Learn how to build an interactive text analytics solution with customization using IBM Watson Studio, Python NLTK, IBM Cloud services, Watson services, and Orient DB.

Classify art using TensorFlow

Learn how to build your own data set and train a TensorFlow model for image classification on a Kubernetes cluster.

Fingerprinting personal data from unstructured text

Build a custom model using Watson Natural Language Understanding and Watson Knowledge Studio.

Analyze Twitter handles and hashtags for sentiment and content

Create charts and graphs for Sentiment, Emotional Tone, and Keywords for Twitter handles and hashtags.

Create a mobile handwritten Hangul translation app

Create a mobile application leveraging TensorFlow that will recognize and translate handwritten Korean characters.

Perform a machine learning exercise

Dive into machine learning by performing an exercise on IBM Watson Studio using Apache SystemML.

Build a recommender with Apache Spark and Elasticsearch

This developer pattern demonstrates the key elements of creating a recommender system by using Apache Spark and Elasticsearch.

Correlate documents from different sources

Correlate content across documents using Python NLTK, Watson Natural Language Understanding (NLU) and IBM Data Science Experience (DSX)

Create an Android calorie-counter app

Built for developers familiar with JavaScript and Node.js that are interested in creating a mobile app that interacts with the camera on a mobile device. Captured food images are identified and processed so that nutritional information can be generated and displayed. This journey makes use of the Watson Node.js SDK to access visual recognition processing.

Assemble a pizza-ordering chatbot dialog

The new Watson Conversation Slots feature allows you to create a complex dialog with fewer nodes. Using slots in this example, we can define the fields in one dialog node and handle the logic in a single node.

Enrich multimedia files using services

Use the IBM Watson Node.js SDK to create a web UI app that enriches multimedia files using speech-to-text conversion, tone analysis, natural language understanding, and visual recognition processing.

Create a news alerting app

Create a news app in Node.js to deliver custom alerts via email for specific products or brands mentioned in the news. The app can also alert user on brand sentiment, related products as well as stock price changes.

Detect voltage anomalies in household IoT devices

Get a head start on developing connected devices in the home. Using Node-RED and Watson IoT APIs, you'll learn how to build a cognitive IoT app that detects irregularities in the voltage of your connected household devices.

Image recognition training with PowerAI notebooks

Use transfer learning to leverage the TensorFlow Inception model and create your own image classifier using a PowerAI Jupyter Notebook.

Use Swift to interpret unstructured data from Hacker News

Learn how to pull data points -- concepts, entities, categories, keywords, sentiment, emotion, etc. -- from Hacker News articles using natural-language service calls from a Swift-based application.

Implement voice controls for a serverless home automation hub

Discover how simple it is to build a home automation hub using natural-language services and OpenWhisk serverless technology.

Mine data breaches for insights

Learn how to use the Watson Discovery Service to import, enrich, and explore your organization's data and mine it for actionable insight.

Create a banking chatbot

Create a banking chatbot with conversation, natural language understanding, anger detection, and answer discovery from FAQ documents.

Create a sports buddy with TJBot and Watson

Use a TJBot with Watson services, Twilio, and to create your own interactive sports buddy that can help you follow your favorite team, get game reminders, stats, and more.

Create an investment management chatbot

Create a Watson Conversation-based financial chatbot that enables you to query your investments, analyze securities, and use multiple interfaces.

Accelerate training of machine learning algorithms

Efficiently build powerful deep learning applications and improve your machine learning speeds quickly.

Create a virtual reality speech sandbox

Add IBM Watson Speech-to-Text and Conversation services to a virtual reality environment built in Unity, the popular 3D development platform.

Related open projects

Adversarial Robustness Toolbox

Explore ART, a toolbox for rapid crafting and analysis of attack and defense methods for machine learning models.

Fabric for Deep Learning (FfDL)

Deep Learning as a Service on Kubernetes

Related tech talks

Analyze song lyrics with Watson


This session considers the influence that AI, and Natural Language Processing can infuse in web design, by demonstrating and explaining apps that explore psychology in song lyrics.

Classify vehicle damage images


Discover a server application that uses pictures of vehicle damage to train a Watson Visual Recognition classifier to identify issues for an insurance industry use case.

AI myth buster for developers – Myth #2: You need to train AI from scratch every time

February 19, 2018

The next set of misconception about Artificial Intelligence is that even though we have an Artificial Intelligence system and these systems don't know anything about your business, you need to start from scratch.

AI myth busters for developers – Myth #1: A PhD to do AI

February 19, 2018

A general set of misconceptions about Artificial Intelligence in organizations is the fact that you need to be a really deep data scientist to be able to harness Artificial Intelligence in your organization

Create an Android calorie-counter app using Watson Visual Recognition service

January 30, 2018

Learn how to build a mobile app that can capture and analyze food images and extract nutritional information

Create Alexa skills with Watson Conversation

January 23, 2018

Alexa is the voice service behind products like the Amazon Echo. In this tech talk replay, learn how to use IBM Cloud Functions (based on Apache OpenWhisk) to integrate Alexa with Watson Conversation.

Make your NAO robot smarter

January 16, 2018

Learn how you can add intelligence to a NAO robot using IBM Data Science Experience and IBM Conversation service.

Discover Facebook hidden usage insights

January 10, 2018

Discover how to combine the power of a Jupyter Notebook, PixieDust, and IBM Watson™ cognitive services to glean useful marketing insight from a vast body of unstructured Facebook data. Learn how to improve brand perception, product performance, customer satisfaction, and audience engagement by taking data from a Facebook Analytics export.

Introduction to Bot Asset Exchange

December 5, 2017

In this tech talk replay, IBM Developer Advocate Anamita Guha provides an overview of the new Bot Asset Exchange and shows you how you can use it to start creating chatbots today.

Implement computer vision for PlayerUnknown’s Battlegrounds live streams

November 15, 2017

Developer advocates Cullen Taylor and Spencer Krum talk about a new project called Rotisserie. Rotisserie is an open source IBM project focused on bringing the concept of the “red zone” in American football to live Twitch streams. Rotisserie focuses on the incredibly popular battle royale video game PlayerUnknown’s Battlegrounds and uses object character recognition technology to interpret how far into a game a particular Twitch streamer is.

Create a cognitive retail chatbot

August 30, 2017

This tech talk showcases an easily configurable chatbot that demonstrates a natural language shopping experience for customers.

Node-RED and IBM Bluemix Overview for the NASA Space App Challenge

April 26, 2017

This video shows a demonstration of how to use Node-RED, IBM Bluemix and Watson Conversation service to quickly create applications that utilize data from NASA in preparation for the NASA SpaceApp Challenge.

Writing Cognitive Swift Apps Tech Talk

March 8, 2017

In this replay, members of the Watson Developer Cloud Swift SDK development team walk you through the process of building Swift apps that use Watson and also introduce you to some application demos that use the SDK. They demonstrate Cognitive Concierge, a restaurant recommendations app written entirely in Swift, which is built using the Kitura web framework and uses the Swift SDK to integrate the Watson Conversation, Speech to Text, and Text to Speech services to enable a conversation with Watson. The Alchemy Language API is used to analyze positive and negative sentiments in reviews, which helps the user decide which restaurant they should go to.

TJBot and Embodied Cognition Tech Talk

February 22, 2017

IBM TJBot is the first kit in the collection of IBM Watson Maker Kits, do-it-yourself open source templates to connect to Watson services in a fun way. TJBot creator and IBM Research “Cool Things Czar” Maryam Ashoori and IBM Researcher Victor Dibia provide a closer look at TJBot, Watson services, and Raspberry Pi-based recipes. You can 3D-print or laser cut the TJBot robot frame and use the recipes to bring TJBot to life.


November 9, 2016

In this presentation, IBM Senior Software Engineer Brian Burns takes a deeper dive into EclairJS and how it interacts with Apache Spark.

Apache SystemML Tech Talk

May 25, 2016

Apache SystemML project leader Luciano Resende explains Apache SystemML and Declarative Machine Learning (DML). Apache SystemML includes linear algebra primitives, statistical functions, and ML-specific constructs that make it easier and more natural to express ML algorithms, making data scientists more productive and freeing data from the underlying input formats and physical representations. Apache SystemML also provides automatic optimization to ensure efficiency and scalability, and runs in MapReduce or Spark environments.

Related Blogs

A developer’s view on IBM’s Open Tech AI strategy

I’m especially proud of is IBM’s clear strategy to create, support, and enhance Open Tech AI. From IBM's Center of Open-Source Data and AI Technologies (CODAIT), whose mission encompasses the end-to-end enterprise AI lifecycle, to the machine learning and deep learning capabilities in IBM Watson Studio, IBM presents a clear and powerful Open Tech...

Continue reading A developer’s view on IBM’s Open Tech AI strategy

Use computer vision to detect and track moving objects in video

The counting cars code pattern Using computer vision to annotate videos is a fun and useful exercise. I recently had a chance to try it out while working on this code pattern. I learned a lot (you might, too), and I think that if you try it out, you’ll think of many useful applications. For...

Continue reading Use computer vision to detect and track moving objects in video