paper-with-me

홈 › Papers

On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic

2024-08-30 · Geonho Hwang, Yeachan Park, Sejun Park

Research into the expressive power of neural networks typically considers real parameters and operations without rounding error. In this work, we study universal approximation property of quantized networks under discrete fixed-point parameters and fixed-point operations that may incur errors due to rounding. We first provide a necessary condition and a sufficient condition on fixed-point arithmetic and activation functions for universal approximation of quantized networks. Then, we show that various popular activation functions satisfy our sufficient condition, e.g., Sigmoid, ReLU, ELU, SoftPlus, SiLU, Mish, and GELU. In other words, networks using those activation functions are capable of universal approximation. We further show that our necessary condition and sufficient condition coincide under a mild condition on activation functions: e.g., for an activation function $\sigma$, there exists a fixed-point number $x$ such that $\sigma(x)=0$. Namely, we find a necessary and sufficient condition for a large class of activation functions. We lastly show that even quantized networks using binary weights in $\{-1,1\}$ can also universally approximate for practical activation functions.

📄 PDF Abstract BibTeX arXiv:2409.00297

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

+ ( 1 ) ⟷ 888 ⟷ ( 829 ) ⟷ 0881 How do I file a claim with Expedia? How do I file a claim with Expedia , call + ( 1 ) ⟷ 888 ⟷ ( 829 ) ⟷ 0881 or + ( 1 ) ⟷ 805 ⟷ ( 330 ) ⟷ 4056 and ask to speak with a manager. Explain your issue in detail and…
(TravEL!!Guide)How Do I File a Claim with Expedia? How Do I File a Claim with Expedia? Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Fast Help & Exclusive Travel Discounts!Need to file a claim with…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
ELU 설명 없음
SiLU Sigmoid Linear Units, or SiLUs, are activation functions for neural networks. The activation of the SiLU is computed by the sigmoid function multiplied by its input, or…
Tanh Activation 설명 없음

Similar Papers 제목 키워드 기반

On the Expressive Power of Weight Quantization in Large Language Models

2026-06-20 · Shao-Qun Zhang arxiv

In recent years, weight quantization that encodes the learnable parameters of large language models in an $n$-bit format has garnered significant attention due to its potential for model compression and inference acceler…

Model Compression

Fixed-point optimization of deep neural networks with adaptive step size retraining

2017-02-27 · Sungho Shin, Yoonho Boo, Wonyong Sung

Fixed-point optimization of deep neural networks plays an important role in hardware based design and low-power implementations. Many deep neural networks show fairly good performance even with 2- or 3-bit precision when…

Quantization

Exact Fixed-Point Constraints in Neural-ODEs with Provable Universality

2026-05-11 · Feliciano Giuseppe Pacifico, Duccio Fanelli, Lorenzo Buffoni, Lorenzo Chicchi 외 arxiv

We introduce a technique that enables Neural-ODEs to approximate arbitrary velocity fields with a priori planted fixed-points. Specifically, a recipe is given to explicitly accommodate for a finite collection of points i…

MRQ:Support Multiple Quantization Schemes through Model Re-Quantization

2023-08-01 · Manasa Manohara, Sankalp Dayal, Tariq Afzal, Rahul Bakshi 외

Despite the proliferation of diverse hardware accelerators (e.g., NPU, TPU, DPU), deploying deep learning models on edge devices with fixed-point hardware is still challenging due to complex model quantization and conver…

modelQuantization

Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms

2021-02-03 · Rishabh Goyal, Joaquin Vanschoren, Victor van Acht, Stephan Nijssen

Convolutional Neural Networks (CNNs) have proven to be a powerful state-of-the-art method for image classification tasks. One drawback however is the high computational complexity and high memory consumption of CNNs whic…

image-classificationImage ClassificationQuantization