High-precision NLP using HDD.
Implementing SoTA algorithms, integrating them into the network to aim for acceleration!
In the field of NLP, one approach to improving accuracy is the introduction of memory layers. However, storing a large amount of memory can lead to the problem of slow retrieval times. To solve this, speeding up approximate nearest neighbor search can enable high accuracy for the network. 【Technical Details】 ■Acceleration of Faiss - Implementing state-of-the-art algorithms and aiming for acceleration by integrating them into the network. ■Development of approximate nearest neighbor search algorithms - Further tuning Faiss to aim for overall acceleration during training. *For more details, please download the PDF or feel free to contact us.
- 企業：スマートホールディングス
- 価格：Other
