Computer poetry generation is our first step towards computer writing. Writing must have a theme. The current approaches of using sequence-to-sequence models with attention often produce non-thematic poems. We present a novel conditional variational autoencoder with a hybrid decoder adding the deconvolutional neural networks to the general recurrent neural networks to fully learn topic information via latent variables. This approach significantly improves the relevance of the generated poems by representing each line of the poem not only in a context-sensitive manner but also in a holistic way that is highly related to the given keyword and the learned topic. A proposed augmented word2vec model further improves the rhythm and symmetry. Tests show that the generated poems by our approach are mostly satisfying with regulated rules and consistent themes, and 73.42% of them receive an Overall score no less than 3 (the highest score is 5).

Implementing deep learning in enterprise settings requires a lot more than just downloading some open source algorithms, but with talent scarce, businesses are finding it takes creativity and an open-minded approach to achieve results. "Established industries are largely missing out on the benefits of AI," said Ryan Kottenstette, co-founder and CEO of Silicon Valley geospatial data company Cape Analytics LLC. "If you're not in the tech sector, you might be waiting a bit longer for the benefits of AI to be realized." In recent years, deep learning has taken huge strides. Algorithmic processes like neural networks, which historically lived more in the realm of mathematical theory, have moved into some enterprise use cases, like computer vision and process automation. But adoption has been uneven.

Recent advancements in computing technologies along with the increasing popularity of ecommerce platforms have radically amplified the risk of online fraud for financial services companies and their customers. Failing to properly recognize and prevent fraud results in billions of dollars of loss per year for the financial industry. This trend has urged companies to look into many popular artificial intelligence (AI) techniques, including deep learning for fraud detection. Deep learning can uncover patterns in tremendously large datasets and independently learn new concepts from raw data without extensive manual feature engineering. For this reason, deep learning has shown superior performance in domains such as object recognition and image classification.

Capsule endoscopy identifies damaged areas in a patient's small intestine but often outputs poor-quality images or misses lesions, leading to either misdiagnosis or repetition of the lengthy procedure. The authors propose applying deep-learning models to automatically process the captured images and identify lesions in real time, enabling the capsule to take additional images of a specific location, adjust its focus level, or improve image quality. The authors also describe the technical challenges in realizing a viable automated capsule-endoscopy system. J. Ahn, H. Nguyen Loc, R. Krishna Balan, Y. Lee and J. Ko, "Finding Small-Bowel Lesions: Challenges in Endoscopy-Image-Based Learning Systems," in Computer, vol.

Recurrent neural networks (RNNs) have shown promising results in audio and speech-processing applications. The increasing popularity of Internet of Things (IoT) devices makes a strong case for implementing RNN-based inferences for applications such as acoustics-based authentication and voice commands for smart homes. However, the feasibility and performance of these inferences on resource-constrained devices remain largely unexplored. The authors compare traditional machine-learning models with deep-learning RNN models for an end-to-end authentication system based on breathing acoustics.

By leveraging advances in deep learning, challenging pattern recognition problems have been solved in computer vision, speech recognition, natural language processing, and more. Mobile computing has also adopted these powerful modeling approaches, delivering astonishing success in the field's core application domains, including the ongoing transformation of human activity recognition technology through machine learning.

Although the ability to collect, collate, and analyze the vast amount of data generated from cyber-physical systems and Internet of Things devices can be beneficial to both users and industry, this process has led to a number of challenges, including privacy and scalability issues. The authors present a hybrid framework where user-centered edge devices and resources can complement the cloud for providing privacy-aware, accurate, and efficient analytics.

How can the advantages of deep learning be brought to the emerging world of embedded IoT devices? The authors discuss several core challenges in embedded and mobile deep learning, as well as recent solutions demonstrating the feasibility of building IoT applications that are powered by effective, efficient, and reliable deep learning models.

To deliver the hardware computation power advances needed to support deep learning innovations, identifying deep learning properties that designers could potentially exploit is invaluable. This article articulates our strategy and overviews several value properties of deep learning models that we identified and some of our hardware designs that exploit them to reduce computation, and on- and off-chip storage and communication.

Mobile and embedded devices increasingly rely on deep neural networks to understand the world--a feat that would have overwhelmed their system resources only a few years ago. Further integration of machine learning and embedded/mobile systems will require additional breakthroughs of efficient learning algorithms that can function under fluctuating resource constraints, giving rise to a field that straddles computer architecture, software systems, and artificial intelligence. N. D. Lane and P. Warden, "The Deep (Learning) Transformation of Mobile and Embedded Computing," in Computer, vol.