Given the destructive impacts of tropical cyclones, it is critical to have a reliable system for cyclone intensity detection. Various techniques are available for this purpose, each with differing levels of accuracy. In this paper, we introduce two ensemble-based models based on AlexNet architecture to estimate tropical cyclone intensity using visible satellite images. The first model, trained on the entire dataset, is called the global AlexNet model. The second model is a distributed version of AlexNet in which multiple AlexNets are trained separately on subsets of the training data categorized according to the Saffir-Simpson wind speed scale prescribed by the meterologists. We evaluated the performance of both models against a deep learning benchmark model called \textit{Deepti} using a publicly available cyclone image dataset. Results indicate that both the global model (with a root mean square error (RMSE) of 9.03 knots) and the distributed model (with a RMSE of 9.3 knots) outperform the benchmark model (with a RMSE of 13.62 knots). We provide a thorough discussion of our solution approach, including an explanantion of the AlexNet's performance using gradient class activation maps (grad-CAM). Our proposed solution strategy allows future experimentation with various deep learning models in both single and multi-channel settings.

Adaptation of a classifier to new domains is one of the challenging problems in machine learning. This has been addressed using many deep and non-deep learning based methods. Among the methodologies used, that of adversarial learning is widely applied to solve many deep learning problems along with domain adaptation. These methods are based on a discriminator that ensures source and target distributions are close. However, here we suggest that rather than using a point estimate obtaining by a single discriminator, it would be useful if a distribution based on ensembles of discriminators could be used to bridge this gap. This could be achieved using multiple classifiers or using traditional ensemble methods. In contrast, we suggest that a Monte Carlo dropout based ensemble discriminator could suffice to obtain the distribution based discriminator. Specifically, we propose a curriculum based dropout discriminator that gradually increases the variance of the sample based distribution and the corresponding reverse gradients are used to align the source and target feature representations. An ensemble of discriminators helps the model to learn the data distribution efficiently. It also provides a better gradient estimates to train the feature extractor. The detailed results and thorough ablation analysis show that our model outperforms state-of-the-art results.

Convolutional Neural Networks (CNNs) are the fundamental building blocks of many deep learning applications. Everyday computer vision solutions to tasks such as image classification, object detection, pose estimation, depth estimation are solved through the implementation of carefully designed CNN architecture. Throughout my academic and professional career, I have found that it's vital to have an in-depth awareness of the internal components that are employed to develop widely used CNN architecture. Transfer Learning and Fine Tuning have made access to state of the art CNN architecture easier. Nonetheless, it is beneficial to take a step back to the simplest architectures and earliest deep learning research papers and understand the initial building blocks of what we today observe as Deep Learning.

Just enter code fccstevens into the promotional discount code box at checkout at manning.com. In part one, we learned about PyTorch and its component parts, now let's take a closer look and see what it can do. In this article, we explore some of PyTorch's capabilities by playing with pre-trained networks. Computer vision -- a field that deals with making computers to gain high-level understanding from digital images or videos -- is certainly one of the fields most impacted by the advent of deep learning, for a variety of reasons. The need for classifying or interpreting the content of natural images was there, huge datasets became available and new constructs, such as convolutional layers, came about and started to run quickly on GPUs with unprecedented accuracies.