Scholarlink

In the previous chapter, we discussed neural networks, building up from a simple model with no layers (i.e., linear regression), to a model with a single hidden layer (two trainable layers in total, hidden + output), and finally discussing ‘deep’ neural networks with many hidden layers. We also discussed different factors in choosing the representation of our data. In this chapter, we will discuss a specific representation—sequences—and types of NNs specifically designed to handle sequences.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Sequence-Based DNN PCGML

  • 章节

  • 发表日期：

    2025年

查看全文
  • Matthew Guzdial,
  • Sam Snodgrass,
  • Adam Summerville

摘要

In the previous chapter, we discussed neural networks, building up from a simple model with no layers (i.e., linear regression), to a model with a single hidden layer (two trainable layers in total, hidden + output), and finally discussing ‘deep’ neural networks with many hidden layers. We also discussed different factors in choosing the representation of our data. In this chapter, we will discuss a specific representation—sequences—and types of NNs specifically designed to handle sequences.