Systematic Analysis of Image Generation using GANs

Generative Adversarial Networks have been crucial in the developments made in unsupervised learning in recent times. Exemplars of image synthesis from text or other images, these networks have shown remarkable improvements over conventional methods in terms of performance. Trained on the adversarial training philosophy, these networks aim to estimate the potential distribution from the real data and then use this as input to generate the synthetic data. Based on this fundamental principle, several frameworks can be generated that are paragon implementations in several real-life applications such as art synthesis, generation of high resolution outputs and synthesis of images from human drawn sketches, to name a few. While theoretically GANs present better results and prove to be an improvement over conventional methods in many factors, the implementation of these frameworks for dedicated applications remains a challenge. This study explores and presents a taxonomy of these frameworks and their use in various image to image synthesis and text to image synthesis applications. The basic GANs, as well as a variety of different niche frameworks, are critically analyzed. The advantages of GANs for image generation over conventional methods as well their disadvantages amongst other frameworks are presented. The future applications of GANs in industries such as healthcare, art and entertainment are also discussed.

Forecasting Model for Crude Oil Price Using Artificial Neural Networks and Commodity Futures Prices

This paper presents a model based on multilayer feedforward neural network to forecast crude oil spot price direction in the short-term, up to three days ahead. A great deal of attention was paid on finding the optimal ANN model structure. In addition, several methods of data pre-processing were tested. Our approach is to create a benchmark based on lagged value of pre-processed spot price, then add pre-processed futures prices for 1, 2, 3,and four months to maturity, one by one and also altogether. The results on the benchmark suggest that a dynamic model of 13 lags is the optimal to forecast spot price direction for the short-term. Further, the forecast accuracy of the direction of the market was 78%, 66%, and 53% for one, two, and three days in future conclusively. For all the experiments, that include futures data as an input, the results show that on the short-term, futures prices do hold new information on the spot price direction. The results obtained will generate comprehensive understanding of the crude oil dynamic which help investors and individuals for risk managements.