Our second example deals with a more challenging problem: the recognition of hand-printed letters of the alphabet. The characters that people print in the ordinary course of filling out forms and questionnaires are surprisingly varied. Gaps abound wherecontinuous lines might be expected; curves and sharp angles appear interchangeably; there is almost every imaginable distortion of slant, shape and size. Even human readers cannot always identify such characters; their error rate is about 3 per cent on randomly selected letters and numbers, seen out of context.
– from Oliver G. Selfridge & Ulric Neisser. PATTERN RECOGNITION BY MACHINE . In Computers & thought, Edward A. Feigenbaum and Julian Feldman (Eds.). MIT Press, Cambridge, MA, USA, 1963. pp. 8-30.
Supervised learning needs labels, or annotations, that tell the algorithm what the right answers are in the training phases of your project. In fact, many of the examples of using MXNet, TensorFlow, and PyTorch start with annotated data sets you can use to explore the various features of those frameworks. Unfortunately, when you move from the examples to application, it's much less common to have a fully annotated set of data at your fingertips. This tutorial will show you how you can use Amazon Mechanical Turk (MTurk) from within your Amazon SageMaker notebook to get annotations for your data set and use them for training. TensorFlow provides an example of using an Estimator to classify irises using a neural network classifier.