Manoj Nambiar

High-Performance Deployment of Text Detection Model: Compression and Hardware Platform considerations

2022

Network compression is often adopted for high throughput implementation on commercial accelerators. We propose a heuristic based approach to obtain compressed networks with a hardware-friendly architecture as an alternative to conventional NAS algorithms that are …

Hetero-Rec++: Modelling-based Robust and Optimal Deployment of Embeddings Recommendations

2023

Deep Neural Network (DNN)-based recommendation models (RMs) are widely adopted in enterprise applications to suggest products, videos, tweets, and posts to users. These models heavily rely on embedding tables, which contain latent embedding vectors and …