Machine Learning Projects with Java

The aim of the video is to learn how we can set up our project using Weka library.

   •  Add Weka library to the project and use Weka API to load train dataset

   •  Analyze weather sensor data

   •  Extract data attribution from sensor data

The aim of the video is to learn how we can do data mining of input dataset.

   •  Analyze statistics data from flowers

   •  Understand the problem of classification

   •  Load training data using Weka

The aim of the video is to learn to build classifier in the Weka library.

   •  Build Bayes classifier based on data

   •  Analyze data used for cross-validation

   •  Write cross validation code and code that assigns features without a label to class

The aim of the video is to perform cross-validation of the model.

   •  Examine starting classifier

   •  Assert classes that were assigned to data

The aim of the video is to make predictions based on the classification.

   •  Start understanding K-means clustering

   •  Model number of classes for weather sensor data

   •  Perform data clustering using Weka

The aim of the video is to learn how we can extract feature vector for housing data.

   •  Analyze housing data in CSV format

   •  Convert CSV to Weka format

   •  Analyze house Weka data

The aim of the video is to learn how we can perform normalization of data.

   •  Understand features normalization

   •  Write house data normalizer

   •  Save normalized house data

The aim of the video is to learn how we can build our regression model.

   •  Build regression for housing data

   •  Gather statistics from the model

The aim of the video is to learn how to leverage the regression model for predicting the price of the house.

   •  Build a K-means clustering algorithm for house data

   •  Gather classes of housing property

   •  Conclude price per cluster

The aim of the video is to learn how to save a model for further re-usage.

   •  Create regression model for house data

   •  Save model for later re-usage

   •  Load the model into Weka back again

The aim of the video is to learn how we can feed our DL4J model with gender labeled data.

   •  Analyze gender input data

   •  Define labels for our data

   •  Understand feature needed for a model

The aim of the video is to create LabeledGenderFromFileLineReader for automatic feature extraction.

   •  Extend LineRecordReader API

   •  Fetch names automatically

   •  Write DL4J custom iterator

The aim of the video is to learn how we can create a neural network with multiple layers.

   •  Load test data set into model

   •  Load train data set into the model

   •  Configure DL network for guessing gender based on the name

The aim of the video is to train our deep learning model.

   •  Write logic for actual network training

   •  Configure UI server for exposing results via web browser

   •  Write logic that performs training

The aim of the video is to perform validation of our model.

   •  Write logic for cross-validation of the model

   •  Start training

   •  Track progress via DL4J UI and analyze results

The aim of the video is to learn how we can extract feature vector from text data.

   •  Analyze raw textual data

   •  Understand how to pass text data as a feature vector to the model

   •  Look at the simplest way of doing the transformation from text to feature vector

The aim of the video is to learn how we can load raw textual data that will be an input for NLP training.

   •  Leverage BasicLineIterator

   •  Tokenize input data

   •  Build available vocabulary

The aim of the video is to learn how we can leverage NLP construct from DL4J.

   •  Build a lookup table based on the feature vector

   •  Build model

   •  Start fitting vectors with textual data

The aim of the video is to find words based on the similarity.

   •  Start model

   •  Write a test for finding similarity between words

   •  Start testing