OpenBLASライブラリを使用した行列型とニューラルネットワークC++ライブラリの実装 #1
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
概要
OpenBLASを使用した高速な行列演算により、C++でニューラルネットワークを簡単に扱えるライブラリを実装しました。
実装内容
主要コンポーネント
1. Matrix クラス (OpenBLAS統合)
2. 活性化関数
3. Layer クラス
4. NeuralNetwork クラス
ビルドシステム
使用例
テスト・検証
ドキュメント
NeuralNetwork.hpp) で全機能を簡単にインクルード可能技術的な特徴
ファイル構成
動作確認
✅ CMakeビルド成功
✅ 全ての単体テスト通過
✅ XOR問題の学習成功(損失 < 0.0002)
✅ OpenBLASによる行列演算の動作確認
このライブラリにより、C++でニューラルネットワークを効率的かつ簡単に実装できるようになりました。
Warning
Firewall rules blocked me from connecting to one or more addresses (expand for details)
I tried to connect to the following addresses, but was blocked by firewall rules:
esm.ubuntu.com/usr/lib/apt/methods/https(dns block)If you need me to access, download, or install something from one of these locations, you can either:
Original prompt
💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click here to start the survey.