中文
相关论文

相关论文: MintNet: Building Invertible Neural Networks with …

200 篇论文

We present new algorithms for adaptively learning artificial neural networks. Our algorithms (AdaNet) adaptively learn both the structure of the network and its weights. They are based on a solid theoretical analysis, including…

机器学习 · 计算机科学 2017-03-01 Corinna Cortes , Xavi Gonzalvo , Vitaly Kuznetsov , Mehryar Mohri , Scott Yang

This paper introduces NeuroBlend, a novel neural network architecture featuring a unique building block known as the Blend module. This module incorporates binary and fixed-point convolutions in its main and skip paths, respectively. There…

硬件体系结构 · 计算机科学 2024-05-02 Arash Fayyazi , Mahdi Nazemi , Arya Fayyazi , Massoud Pedram

Graph prediction problems prevail in data analysis and machine learning. The inverse prediction problem, namely to infer input data from given output labels, is of emerging interest in various applications. In this work, we develop…

机器学习 · 统计学 2022-11-22 Chen Xu , Xiuyuan Cheng , Yao Xie

Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. One standard strategy is to apply data augmentation to synthetically enlarge the training set.…

计算机视觉与模式识别 · 计算机科学 2020-06-29 Yunhan Zhao , Ye Tian , Charless Fowlkes , Wei Shen , Alan Yuille

In large-scale distributed scenarios, increasingly complex tasks demand more intelligent collaboration across networks, requiring the joint extraction of structural representations from data samples. However, conventional task-specific…

机器学习 · 计算机科学 2026-04-21 Zhuojun Tian , Chaouki Ben Issaid , Mehdi Bennis

The generalization error of deep neural networks via their classification margin is studied in this work. Our approach is based on the Jacobian matrix of a deep neural network and can be applied to networks with arbitrary non-linearities…

机器学习 · 统计学 2017-07-04 Jure Sokolic , Raja Giryes , Guillermo Sapiro , Miguel R. D. Rodrigues

Implicit neural networks are a general class of learning models that replace the layers in traditional feedforward models with implicit algebraic equations. Compared to traditional learning models, implicit networks offer competitive…

机器学习 · 计算机科学 2021-12-13 Saber Jafarpour , Matthew Abate , Alexander Davydov , Francesco Bullo , Samuel Coogan

Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accuracy. However, as a model of the brain they are seriously…

机器学习 · 计算机科学 2022-01-19 Roman Pogodin , Yash Mehta , Timothy P. Lillicrap , Peter E. Latham

In this work, we develop a neural architecture search algorithm, termed Resbuilder, that develops ResNet architectures from scratch that achieve high accuracy at moderate computational cost. It can also be used to modify existing…

Convolutional neural networks typically contain several downsampling operators, such as strided convolutions or pooling layers, that progressively reduce the resolution of intermediate representations. This provides some shift-invariance…

机器学习 · 计算机科学 2022-02-04 Rachid Riad , Olivier Teboul , David Grangier , Neil Zeghidour

This paper introduces an Interpretable Neural Network (INN) incorporating spatial information to tackle the opaque parameterization process of random weighted neural networks. The INN leverages spatial information to elucidate the…

机器学习 · 计算机科学 2024-04-16 Jing Nan , Wei Dai

Deep neural networks have usually to be compressed and accelerated for their usage in low-power, e.g. mobile, devices. Recently, massively-parallel hardware accelerators were developed that offer high throughput and low latency at low power…

机器学习 · 计算机科学 2021-08-04 Thomas Pfeil

With the maturing of deep learning systems, trustworthiness is becoming increasingly important for model assessment. We understand trustworthiness as the combination of explainability and robustness. Generative classifiers (GCs) are a…

计算机视觉与模式识别 · 计算机科学 2020-12-03 Radek Mackowiak , Lynton Ardizzone , Ullrich Köthe , Carsten Rother

The basic computational unit in Capsule Network (CapsNet) is a capsule (vs. neurons in Convolutional Neural Networks (CNNs)). A capsule is a set of neurons, which form a vector. CapsNet is used for supervised classification of data and has…

计算机视觉与模式识别 · 计算机科学 2025-10-10 Pouya Shiri , Ramin Sharifi , Amirali Baniasadi

We introduce the concept of dynamically growing a neural network during training. In particular, an untrainable deep network starts as a trainable shallow network and newly added layers are slowly, organically added during training, thereby…

神经与进化计算 · 计算机科学 2015-11-24 Leslie N. Smith , Emily M. Hand , Timothy Doster

Unstructured pruning has the limitation of dealing with the sparse and irregular weights. By contrast, structured pruning can help eliminate this drawback but it requires complex criterion to determine which components to be pruned. To this…

计算机视觉与模式识别 · 计算机科学 2022-05-04 Weichao Lan , Yiu-ming Cheung , Juyong Jiang

Deep neural networks exhibit remarkable performance, yet their black-box nature limits their utility in fields like healthcare where interpretability is crucial. Existing explainability approaches often sacrifice accuracy and lack…

机器学习 · 计算机科学 2025-04-08 Linhui Huang , Sayeri Lala , Niraj K. Jha

In recent work it has been shown that determining a feedforward ReLU neural network to within high uniform accuracy from point samples suffers from the curse of dimensionality in terms of the number of samples needed. As a consequence,…

机器学习 · 统计学 2024-11-11 Yuanyuan Li , Philipp Grohs , Philipp Petersen

This paper proposes to learn high-performance deep ConvNets with sparse neural connections, referred to as sparse ConvNets, for face recognition. The sparse ConvNets are learned in an iterative way, each time one additional layer is…

计算机视觉与模式识别 · 计算机科学 2015-12-08 Yi Sun , Xiaogang Wang , Xiaoou Tang

Variational methods are widely applied to ill-posed inverse problems for they have the ability to embed prior knowledge about the solution. However, the level of performance of these methods significantly depends on a set of parameters,…