RESTful AI Demo

Figure 1. Photo by Growtika on Unsplash

Table of contents

1. Introduction
2. Definitions of machine learning and deep learning
   1. Machine learning
   2. Deep learning

Introduction

RESTful AI Demo (RAID) is a simple set of APIs for learning machine learning (ML) and deep learning (DL). It is written in Java Spring Boot and consists of two components:

• Zoo Chatbot (ML): enquires about a zoo, based on Apache OpenNLP natural language processing (NLP).

• Handwriting Recogniser (DL): recognition of handwritten digits, based on Deep Java Library (DJL) image recognition.

Definitions of machine learning and deep learning

ML is a subset of AI and DL is a subset of ML:

Figure 2. AI vs. ML vs. DL

Machine learning

• Typically involves providing an algorithm with example input and corresponding output data, then letting the algorithm run iteratively to learn the nature of these mappings

• Iteratively adjusts its parameters and compares its calculated output, derived from the input, to the defined output

• Once the model is trained in this manner it can predict the classification of relevant input

Deep learning

• Similar to ML in that it also learns through an iterative algorithm

• Typically uses much more input data and stores its calculations in a neural network structure

• The data and relationships of data are stored as nodes and weighted vectors

• Powerful enough to learn on its own, without provision of example output

For a deeper understanding of the inner workings of ML and DL, see these deep dives:

• Zoo Chatbot deep dive

• Handwriting Recogniser deep dive