Machine Learning Development
Machine learning turns complex data into real-world insights, ranging from customized marketing and fraud detection to supply chain optimization and personalized medicine. Choose the right type of machine learning for your application and begin developing using software optimized for Intel hardware.
Use Cases
Machine learning is used in a broad range of use cases. Companies that integrate machine learning applications into their processes often see substantial competitive advantages such as increased revenue, lower costs, and more efficient operations.
Anomaly Detection
Analyze large amounts of data, often streaming in over time, to identify significant deviations or outliers that could indicate potential problems.
Prediction
Use historical data to create a model for complex relationships between variables to predict future outcomes based on observed data.
Classification
Categorize new observations using a model trained on a multi-variable labeled dataset.
Segmentation
Combine attribute and behavioral data over time to create groups based on relevant characteristics.
Types of Machine Learning
There are three types of machine learning: supervised, unsupervised, and reinforcement. The type used depends upon the kind of data being analyzed and the task to be accomplished.
Supervised Learning
This method uses labeled datasets that are trained to identify specific target variables. There are two categories of supervised learning: classification, which is used to predict categorical outcomes like the quality of a product, and regression, which is used to predict continuous outcomes like the number of products sold.
Unsupervised Learning
This method is used when input datasets are not labeled, and is used to uncover patterns and commonalities within the data. Use cases include clustering and segmentation, association rules, and dimensionality reduction.
Reinforcement Learning
With this method, an input dataset is not required; data is generated through a feedback system during training. The model continuously learns through feedback from previous actions. Robotics and gaming commonly use this method to maximize the cumulative reward based on past experiences.
Real-World Example: Machine Learning for Customer Segmentation
A large, multinational retailer wants to create a series of targeted marketing campaigns. Using customer segmentation, they can quickly identify shoppers with shared purchasing characteristics.
1. Explore
Cleanse online purchase transactions from a multinational retailer and visualize them.
2. Train
Apply unsupervised learning to train AI-based clustering algorithms to identify critical transactions and customer segmentation categories. Notice that the green clusters are separate from the red clusters, indicating distinct customer segments.
3. Infer
Input new customer purchase transactions into the clustering algorithms.
4. Monitor
The clusters move together and become less distinguishable as the model drifts over time.
Machine Learning Development Software and Ecosystem
Intel develops software and contributes optimizations to open source machine learning tools so you can get the fastest training turnaround and lowest inference latency from your available hardware while using your preferred tools.
Example Applications and Pipelines
Recommended Resources
Introduction to Machine Learning
This course provides an overview of machine learning fundamentals on modern Intel architecture.
Optimize Utility Maintenance Prediction for Better Service
Learn how to build and optimize model training and inference across a heterogeneous XPU architecture with little to no code changes.
Build an End-to-End Machine Learning Workflow
Download and try a code sample that covers data preparation, model training, and ridge regression using US census data.
How Smart Enterprises Get Ahead with Machine Learning
Machine learning helps organizations improve and reinvent business processes, identify new market opportunities, and mitigate known and unknown risks.