相关论文: Institutionally Distributed Deep Learning Networks

We study whether deep networks for medical imaging learn useful nonrobust features - predictive input patterns that are not human interpretable and highly susceptible to small adversarial perturbations - and how these features impact test…

Transfer learning is a critical technique in training deep neural networks for the challenging medical image segmentation task that requires enormous resources. With the abundance of medical image data, many research institutions release…

Quantum machine learning is emerging as a promising application of quantum computing due to its distinct way of encoding and processing data. It is believed that large-scale quantum machine learning demonstrates substantial advantages over…

Communication scene recognition has been widely applied in practice, but using deep learning to address this problem faces challenges such as insufficient data and imbalanced data distribution. To address this, we designed a weighted loss…

Current research has found that some deep neural networks exhibit strong hierarchical self-similarity in feature representation or parameter distribution. However, aside from preliminary studies on how the power-law distribution of weights…

Deep reinforcement learning (RL) algorithms have achieved great success on a wide variety of sequential decision-making tasks. However, many of these algorithms suffer from high sample complexity when learning from scratch using…

Federated learning enables multiple institutions to collaboratively train machine learning models on their local data in a privacy-preserving way. However, its distributed nature often leads to significant heterogeneity in data…

The class distribution of data is one of the factors that regulates the performance of machine learning models. However, investigations on the impact of different distributions available in the literature are very few, sometimes absent for…

This study introduces a novel unsupervised medical image feature extraction method that employs spatial stratification techniques. An objective function based on weight is proposed to achieve the purpose of fast image recognition. The…

While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment.…

While a key component to the success of deep learning is the availability of massive amounts of training data, medical image datasets are often limited in diversity and size. Transfer learning has the potential to bridge the gap between…

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…

Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions. This issue of deep neural networks has led to a number of…

Transferring a deep neural network trained on one problem to another requires only a small amount of data and little additional computation time. The same behaviour holds for ensembles of deep learning models typically superior to a single…

Deep learning models for medical data are typically trained using task specific objectives that encourage representations to collapse onto a small number of discriminative directions. While effective for individual prediction problems, this…

Big neural networks trained on large datasets have advanced the state-of-the-art for a large variety of challenging problems, improving performance by a large margin. However, under low memory and limited computational power constraints,…

Deep learning methods have shown great promise in many practical applications, ranging from speech recognition, visual object recognition, to text processing. However, most of the current deep learning methods suffer from scalability…

Nowadays, data-driven, machine and deep learning approaches have provided unprecedented performance in various complex tasks, including image classification and object detection, and in a variety of application areas, like autonomous…

Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. In contrast to static methods that repeat the quantization process and train different models…

Relying on either deep models or physical models are two mainstream approaches for solving inverse sample reconstruction problems in programmable illumination computational microscopy. Solutions based on physical models possess strong…