Classification and Regression with the BigML Dashboard
5.1 Introduction
There are multiple Machine Learning problems that can be solved using Supervised learning Machine Learning techniques. Some of these problems require to predict an output variable (Objective Field) given a number of input variables (input Fields). These problems can be divided into Classification and Regression depending on whether you need to predict a category (label or class) or a continuous value (a real number), respectively. To learn more about concrete use cases for both problems refer to section 1.1 .
Deep neural networks (or deepnets) are a Machine Learning technique that can be used to solve classification and regression problems. These problems can also be solved with other Machine Learning methods, such as models, ensembles, or logistic regressions. These methods are explained in Chapter 1 , Chapter 2 , and Chapter 4 respectively. Depending on the problem you are trying to solve and the data available, some techniques may perform significantly better than others. See in subsection 5.2.3 a detailed explanation of how deepnets perform compared to other supervised learning techniques for different use cases.
Deepnets are a class of machine learning models inspired by the neural circuitry of the human brain. See section 5.2 for more details on the deepnets algorithm.
This chapter contains comprehensive description of BigML’s deepnets including how they can be created with 1-click (section 5.3 ), all configuration options available (section 5.4 ), and the different visualizations provided by BigML (section 5.5 ). See section 5.6 for an explanation of how deepnets can be used to make predictions. You can also export your deepnets in different formats to make local predictions faster at no cost (subsection 5.7.1 ). The process to evaluate your deepnets predictive performance in BigML is explained in a different chapter (Chapter 7 ).
In BigML, the third tab of the main menu of the Dashboard allows you to list all of your available deepnets. The deepnet list view (Figure 5.1 ), details the Dataset used to create it, the Name, Objective (Objective Field name), Age (time elapsed since it was created), Size, and number of evaluations, predictions, and batch predictions that have been created using that deepnet. The search menu option in the top right corner of the deepnet list view allows you to search your deepnets by name.
![\includegraphics[]{images/deepnet/deepnet-listings}](images/img-0455.png)
By default, when you first create an account at BigML, or every time that you start a new Project, your list of deepnets will be empty. (See Figure 5.2 .)
![\includegraphics[]{images/deepnet/empty-deepnet-listings}](images/img-0456.png)
Finally, in Figure 5.3 you can see the icon used to represent a deepnet.
![\includegraphics[width=2cm]{images/deepnet/deepnet-icon}](images/img-0457.png)