> For the complete documentation index, see [llms.txt](https://deeplearning4j.konduit.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://deeplearning4j.konduit.ai/core-concepts.md).

# Core Concepts

- [Ecosystem Overview](https://deeplearning4j.konduit.ai/core-concepts/ecosystem-overview.md): Overview of the Eclipse Deeplearning4j ecosystem — ND4J, DL4J, DataVec, SameDiff, Python4J, and OmniHub
- [Tensors and NDArrays](https://deeplearning4j.konduit.ai/core-concepts/tensors-and-ndarrays.md): INDArray fundamentals — shape, rank, stride, DataType, creating arrays, views vs copies, and off-heap memory in ND4J
- [Data Pipelines](https://deeplearning4j.konduit.ai/core-concepts/data-pipelines.md): Loading, transforming, and feeding data for training — RecordReader, DataSetIterator, normalization, and mini-batching
- [Neural Network Fundamentals](https://deeplearning4j.konduit.ai/core-concepts/neural-net-fundamentals.md): Layers, activation functions, loss functions, weight initialization, and regularization in Deeplearning4j
- [The Training Loop](https://deeplearning4j.konduit.ai/core-concepts/training-loop.md): Building, configuring, and training neural networks — NeuralNetConfiguration, updaters, fit(), listeners, and ComputationGraph
- [Evaluation](https://deeplearning4j.konduit.ai/core-concepts/evaluation.md): Evaluating model performance — classification metrics, ROC curves, regression metrics, and evaluation during training
- [Memory and Workspaces](https://deeplearning4j.konduit.ai/core-concepts/memory-and-workspaces.md): Off-heap memory management, JVM configuration, workspace modes, and troubleshooting memory issues in ND4J and DL4J


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://deeplearning4j.konduit.ai/core-concepts.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.