Appendix A. Chapter Review Answers
Chapter 1: AI Is Magic
-
Machine learning is a subset of AI that is focused on systems that learn from data to improve their performance.
-
You can recommend that the best way to get results would be to collect a set of labeled data, so you can perform supervised or semisupervised training, or you could offer an unsupervised or reinforcement-based approach.
-
Reinforcement learning is the most likely fit for applying machine learning to a game.
-
No, machine learning is a subset of AI.
-
No, a model contains structure and numbers but is generally exponentially smaller than the training data it’s seen.
-
Data is often broken into train and test sets, with some people utilizing validation sets. The training dataset is always the largest.
Chapter 2: Introducing TensorFlow.js
-
No, TensorFlow works directly with Python. You need TensorFlow.js to run AI in the browser.
-
Yes, TensorFlow.js has access to the browser GPU via WebGL, and if you load
tensorflow/tfjs-node-gpu, you can access the server GPU via CUDA. -
No, the TensorFlow.js vanilla and Node.js builds both function without CUDA.
-
You’ll be served the latest version of that library, which may include breaking changes on your site.
-
The classifier returns an array of violations and their percentage of likeliness for being true.
-
A threshold is an optional parameter that can be passed to the model’s
loadcall. -
No, the Toxicity model code requires the network weights for the model, ...