For the culmination of the course CMPS 242, Machine Learning, the authors 1 present a method for image colorization using convolutional neural networks. 2 Colorization, taking a black and white image and turning into a color (RGB) image, 3 is inherently an underdetermined problem. Because of this we aim to generate 4 plausible colorizations using the technology of convolutional neural networks. 5

Artificial neural networks have recently shown great results in many disciplines and a variety of applications, including natural language understanding, speech processing, games and image data generation. One particular application in which the strong performance of artificial neural networks was demonstrated is the recognition of objects in images, where deep convolutional neural networks are...

I present a new way to parallelize the training of convolutional neural networks across multiple GPUs. The method scales significantly better than all alternatives when applied to modern convolutional neural

The last decade has witnessed the success of the traditional feature-based method on exploiting the discrete structures such as words or lexical patterns to extract relations from text. Recently, convolutional and recurrent neural networks has provided very effective mechanisms to capture the hidden structures within sentences via continuous representations, thereby significantly advancing the ...

Lung nodule classification is a class imbalanced problem because nodules are found with much lower frequency than non-nodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We therefore propose cascaded convolutional neural networks to cope with the class imbalanced problem. In the proposed approach, multi-s...

We present AI, the first sound and scalable analyzer for deep neural networks. Based on overapproximation, AI can automatically prove safety properties (e.g., robustness) of realistic neural networks (e.g., convolutional neural networks). The key insight behind AI is to phrase reasoning about safety and robustness of neural networks in terms of classic abstract interpretation, enabling us to le...

Lung nodule detection is a class imbalanced problem because nodules are found with much lower frequency than nonnodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We therefore propose cascaded convolutional neural networks to cope with the class imbalanced problem. In the proposed approach, cascaded conv...

Convolutional auto-encoders have shown their remarkable performance in stacking to deep convolutional neural networks for classifying image data during past several years. However, they are unable to construct the state-of-the-art convolutional neural networks due to their intrinsic architectures. In this regard, we propose a flexible convolutional auto-encoder by eliminating the constraints on...