paper-with-me

홈 › Papers

Quantized Memory-Augmented Neural Networks

2017-11-10 · Seongsik Park, Seijoon Kim, Seil Lee, Ho Bae, Sungroh Yoon

Memory-augmented neural networks (MANNs) refer to a class of neural network models equipped with external memory (such as neural Turing machines and memory networks). These neural networks outperform conventional recurrent neural networks (RNNs) in terms of learning long-term dependency, allowing them to solve intriguing AI tasks that would otherwise be hard to address. This paper concerns the problem of quantizing MANNs. Quantization is known to be effective when we deploy deep models on embedded systems with limited resources. Furthermore, quantization can substantially reduce the energy consumption of the inference procedure. These benefits justify recent developments of quantized multi layer perceptrons, convolutional networks, and RNNs. However, no prior work has reported the successful quantization of MANNs. The in-depth analysis presented here reveals various challenges that do not appear in the quantization of the other networks. Without addressing them properly, quantized MANNs would normally suffer from excessive quantization error which leads to degraded performance. In this paper, we identify memory addressing (specifically, content-based addressing) as the main reason for the performance degradation and propose a robust quantization method for MANNs to address the challenge. In our experiments, we achieved a computation-energy gain of 22x with 8-bit fixed-point and binary quantization compared to the floating-point implementation. Measured on the bAbI dataset, the resulting model, named the quantized MANN (Q-MANN), improved the error rate by 46% and 30% with 8-bit fixed-point and binary quantization, respectively, compared to the MANN quantized using conventional techniques.

📄 PDF Abstract BibTeX arXiv:1711.03712

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

Efficient Execution of Quantized Deep Learning Models: A Compiler Approach

2020-06-18 · Animesh Jain, Shoubhik Bhattacharya, Masahiro Masuda, Vin Sharma 외

A growing number of applications implement predictive functions using deep learning models, which require heavy use of compute and memory. One popular technique for increasing resource efficiency is 8-bit integer quantiz…

CPUDeep LearningQuantization

FineServe: Precision-Aware KV Slab and Two-Level Scheduling for Heterogeneous Precision LLM Serving

2025-09-08 · Kyungmin Bin, Seungbeom Choi, Jimyoung Son, Jieun Choi 외 arxiv

Recent advances in Post-Training Quantization (PTQ) techniques have significantly increased demand for serving quantized large language models (LLMs), enabling higher throughput and substantially reduced memory usage wit…

Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost

2026-02-03 · Yinggan Xu, Kajetan Schweighofer, Risto Miikkulainen, Xin Qiu arxiv

Post-Training Quantization (PTQ) is essential for deploying Large Language Models (LLMs) on memory-constrained devices, yet it renders models static and difficult to fine-tune. Standard fine-tuning paradigms, including R…

Reinforcement Learning

A Fine-tuning Enhanced RAG System with Quantized Influence Measure as AI Judge

2024-02-26 · Keshav Rangan, Yiqiao Yin

This study presents an innovative enhancement to retrieval-augmented generation (RAG) systems by seamlessly integrating fine-tuned large language models (LLMs) with vector databases. This integration capitalizes on the c…

Chatbotparameter-efficient fine-tuningRAGRetrieval+1

FaTRQ: Tiered Residual Quantization for LLM Vector Search in Far-Memory-Aware ANNS Systems

2026-01-15 · Tianqi Zhang, Flavio Ponzina, Tajana Rosing arxiv

Approximate Nearest-Neighbor Search (ANNS) is a key technique in retrieval-augmented generation (RAG), enabling rapid identification of the most relevant high-dimensional embeddings from massive vector databases. Modern …