Single neuron application
We have learnt a lot of technical and mathematical stuff about single neurons, so I really want to walk you through the application on single neurons with respect to the word2vec model. So let's begin!
If you want to build a model that identifies the words that are edible and that are not, then we can use a single neuron to build the model. This kind of application, where we are segregating words either into edible classes or non-edible classes is called a binary classification task. For this kind of task, neurons are used to take one-hot encoded vectors as input and a single neuron will learn which words are related to edible items and which are not related to edible items. So, it will generate a look up table, ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access