Related papers: Large Scale Evolution of Convolutional Neural Netw…
Convolutional Neural Networks (CNNs) define an exceptionally powerful class of models for image classification, but the theoretical background and the understanding of how invariances to certain transformations are learned is limited. In a…
In recent years, deep learning has achieved great success in many computer vision applications. Convolutional neural networks (CNNs) have lately emerged as a major approach to image classification. Most research on CNNs thus far has focused…
Recent literature has shown that convolutional neural networks (CNNs) with large kernels outperform vision transformers (ViTs) and CNNs with stacked small kernels in many computer vision tasks, such as object detection and image…
Neuro-Evolution is a field of study that has recently gained significantly increased traction in the deep learning community. It combines deep neural networks and evolutionary algorithms to improve and/or automate the construction of neural…
The performance of Convolutional Neural Networks (CNNs) highly relies on their architectures. In order to design a CNN with promising performance, extended expertise in both CNNs and the investigated problem is required, which is not…
Convolutional neural networks have achieved great success in various vision tasks; however, they incur heavy resource costs. By using deeper and wider networks, network accuracy can be improved rapidly. However, in an environment with…
The ability of Convolutional Neural Networks (CNNs) to accurately process real-time telemetry has boosted their use in safety-critical and high-performance computing systems. As such systems require high levels of resilience to errors, CNNs…
In this paper, we study 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While efficient, the lacking of representational capability and the training difficulty impede 1-bit CNNs from…
Due to memory constraints on current hardware, most convolution neural networks (CNN) are trained on sub-megapixel images. For example, most popular datasets in computer vision contain images much less than a megapixel in size (0.09MP for…
Exoplanet observations are currently analysed with Bayesian retrieval techniques. Due to the computational load of the models used, a compromise is needed between model complexity and computing time. Analysis of data from future facilities,…
Modern artificial intelligence works typically train the parameters of fixed-sized deep neural networks using gradient-based optimization techniques. Simple evolutionary algorithms have recently been shown to also be capable of optimizing…
In recent years, the research community has discovered that deep neural networks (DNNs) and convolutional neural networks (CNNs) can yield higher accuracy than all previous solutions to a broad array of machine learning problems. To our…
Deep artificial neural networks (DNNs) are typically trained via gradient-based learning algorithms, namely backpropagation. Evolution strategies (ES) can rival backprop-based algorithms such as Q-learning and policy gradients on…
In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While being efficient, the classification accuracy of the current 1-bit CNNs is much worse compared to their…
Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i.e., models with more MACs typically achieve better accuracy, such as EfficientNet and RegNet. These works try to enlarge all the stages…
Convolutional neural networks (CNN) are widely used in computer vision, especially in image classification. However, the way in which information and invariance properties are encoded through in deep CNN architectures is still an open…
A key feature of intelligent behaviour is the ability to learn abstract strategies that scale and transfer to unfamiliar problems. An abstract strategy solves every sample from a problem class, no matter its representation or complexity --…
An important part of breast cancer staging is the assessment of the sentinel axillary node for early signs of tumor spreading. However, this assessment by pathologists is not always easy and retrospective surveys often requalify the status…
Data augmentation refers to a group of techniques whose goal is to battle limited amount of available data to improve model generalization and push sample distribution toward the true distribution. While different augmentation strategies…
Convolutional neural network (CNN) architectures have traditionally been explored by human experts in a manual search process that is time-consuming and ineffectively explores the massive space of potential solutions. Neural architecture…