Skip to content
Tagged articles

quantization

202 articles · Page 3 of 3
Hulu Beijing
Hulu Beijing
Apr 30, 2019 · Artificial Intelligence

How Can Deep Neural Networks Be Accelerated and Compressed? Key Techniques Explained

This article reviews why deep neural networks are over‑parameterized, outlines the challenges of deploying them on mobile and embedded devices, and presents six major strategies—pruning, low‑rank approximation, filter selection, quantization, knowledge distillation, and novel architecture design—to accelerate and compress models while preserving performance.

Model Accelerationdeep learningknowledge distillation
0 likes · 11 min read
How Can Deep Neural Networks Be Accelerated and Compressed? Key Techniques Explained
Tencent Architect
Tencent Architect
Nov 13, 2017 · Artificial Intelligence

Survey of Bandwidth Optimization Techniques in AI Accelerators

This article reviews various architectural strategies—including streaming processing, on‑chip memory optimization, bit‑width compression, sparsity techniques, on‑chip models with chip‑level interconnects, and emerging technologies such as binary networks, memristors, and HBM—to alleviate bandwidth bottlenecks in FPGA/ASIC/TPU AI accelerators.

AIASICAccelerators
0 likes · 20 min read
Survey of Bandwidth Optimization Techniques in AI Accelerators