Many software developers view machine and deep learning as rocket science: too complicated and not living up to its full potential. Without an understanding of machine learning’s underlying principles, it can seem too complex to tackle. For those who do leap in and get started, it can be hard to determine what tools to use. For those already implementing some form of machine learning, the concept of continuous learning (what we humans do as a matter of course in our daily lives) seems out of reach: it takes too long to manage, move, and (re)train models, given the amount of data needed to create a reasonably accurate model.
But continuous machine and deep learning is attainable. With the GridGain resources below, gain a basic understanding of machine and deep learning, hands-on machine learning experience with Apache® Ignite®, help getting machine learning up and running quickly, and tips to avoid some of the more common machine learning challenges.
- Using In-Memory Computing for Continuous Machine and Deep Learning Part 1: Machine and Deep Learning Primer
- Using In-Memory Computing for Continuous Machine and Deep Learning Part 2: Machine and Deep Learning Primer
- Introduction to Machine Learning with Apache Ignite
- Using Linear Regression with Apache Ignite
- Using k-NN Classification with Apache Ignite
- Using K-Means Clustering with Apache Ignite
- Apache Ignite Machine Learning for Fraud Detection
- Genetic Algorithms with Apache Ignite
- Introduction to using TensorFlow™ with Apache Ignite