Born Book Appendix D: References

Forum topic · QianXun · 2026-06-13

Summary

Appendix D of the serialized technical book Born compiles the complete reference list for the book, organized by topic. It covers deep learning foundations (LeCun's MNIST/LeNet-5 work, Adam optimizer, batch normalization), Transformers and large language models (Attention Is All You Need, LLaMA, RoPE), inference optimization (FlashAttention, KV-cache scaling analysis), model formats (ONNX, GGUF), GPU computing (W3C WebGPU specification), and related frameworks that inspired Born's design, including Burn, Gorgonia, and llama.cpp. An online resources table links to the Born GitHub repository, official Go documentation, WebGPU samples, and HuggingFace. The appendix marks the final post of the serial: all 22 chapters and 4 appendices of Born have now been published. The references serve readers who want to trace the academic papers, standards, and open-source projects behind the book's coverage of building deep learning systems in Go.

Appendix D: References

This appendix lists the technical papers, standards documents, and open-source projects cited throughout the book *Born*.

Deep Learning Foundations

1. LeCun et al. (1998). Gradient-based learning applied to document recognition. *Proc. IEEE*. — MNIST and LeNet-5 2. Kingma & Ba (2015). Adam: A method for stochastic optimization. *ICLR*. — Adam optimizer 3. Ioffe & Szegedy (2015). Batch normalization. *ICML*. — Batch normalization

Transformers and Large Language Models

4. Vaswani et al. (2017). Attention is all you need. *NeurIPS*. — Transformer 5. Touvron et al. (2023). LLaMA: Open and efficient foundation language models. *Meta AI*. — LLaMA architecture 6. Su et al. (2021). RoFormer: Enhanced transformer with rotary position embedding. — RoPE

Inference Optimization

7. Dao et al. (2022). FlashAttention: Fast and memory-efficient exact attention. *NeurIPS*. — Flash Attention 8. Pope et al. (2023). Efficiently scaling transformer inference. — KV-cache analysis

Model Formats

9. ONNX (2017–present). https://onnx.ai/ — Open Neural Network Exchange format 10. Gerganov (2023). GGUF format specification. *llama.cpp*. — GGUF format

GPU Computing

11. W3C (2023). WebGPU Specification. https://www.w3.org/TR/webgpu/ — WebGPU standard

Related Frameworks

12. Burn (2023–present). https://burn.dev/ — Rust deep learning framework, an inspiration for Born's design 13. Gorgonia (2016–present). https://gorgonia.org/ — Early deep learning effort in Go 14. llama.cpp (2023–present). https://github.com/ggerganov/llama.cpp — C++ LLM inference engine

Online Resources

| Resource | URL | |----------|-----| | Born official repository | https://github.com/born-ml/born | | Go official documentation | https://go.dev/doc/ | | WebGPU tutorials | https://webgpu.github.io/webgpu-samples/ | | HuggingFace | https://huggingface.co/ |

---

📘 *Born* is a serialized technical book; this is Appendix D of 4.

With this post, all 22 chapters and 4 appendices of the book have been published. Thank you for reading!