Super Efficient Neural Network for Compression Artifacts Reduction and Super Resolution

no code implementations • 26 Jan 2024 • Wen Ma, Qiuwen Lou, Arman Kazemi, Julian Faraone, Tariq Afzal

Video quality can suffer from limited internet speed while being streamed by users.

Efficient Neural Network Super-Resolution

MRQ:Support Multiple Quantization Schemes through Model Re-Quantization

no code implementations • 1 Aug 2023 • Manasa Manohara, Sankalp Dayal, Tariq Afzal, Rahul Bakshi, Kahkuen Fu

Accordingly, deep learning models cannot be easily quantized for diverse fixed-point hardwares, mainly due to slightly different quantization requirements.

Quantization

Accelerator-Aware Training for Transducer-Based Speech Recognition

no code implementations • 12 May 2023 • Suhaila M. Shakiah, Rupak Vignesh Swaminathan, Hieu Duy Nguyen, Raviteja Chinta, Tariq Afzal, Nathan Susanj, Athanasios Mouchtaris, Grant P. Strimel, Ariya Rastrow

Machine learning model weights and activations are represented in full-precision during training.

Quantization speech-recognition +1

Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition

no code implementations • 30 Jun 2022 • Kai Zhen, Hieu Duy Nguyen, Raviteja Chinta, Nathan Susanj, Athanasios Mouchtaris, Tariq Afzal, Ariya Rastrow

We present a novel sub-8-bit quantization-aware training (S8BQAT) scheme for 8-bit neural network accelerators.

Quantization speech-recognition +1

A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation

no code implementations • CVPR 2017 • Chunpeng Wu, Wei Wen, Tariq Afzal, Yongmei Zhang, Yiran Chen, Hai Li

Our DNN has 4. 1M parameters, which is only 6. 7% of AlexNet or 59% of GoogLeNet.

Classification Domain Adaptation +3