No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

Generative models are broadly used in many subfields of DL. DNNs have recently developed a core approach to solving data-centric problems in image classification, translation, etc. The latest developments in parameterizing these models using DNNs and stochastic optimization algorithms have allowed scalable modeling of complex, high-dimensional data, including speech, text, and image. This dissertation proposal presents our state-the-art probabilistic bases and DL algorithms for generative models, including VAEs, GANs, and RNN-based encoder-decoder. The proposal also discusses application areas that may benefit from deep generative models in both NLP and computer vision. In NLP, we proposed an Arabic poetry generation model with extended phonetic and semantic embeddings (Phonetic CNN_subword embeddings). Extensive quantitative experiments using BLEU scores and Hamming distance show notable enhancements over strong baselines. Additionally, a comprehensive human evaluation confirms that the poems generated by our model outperform the base models in criteria including meaning, coherence, fluency, and poeticness. We proposed a generative video model using a hybrid VAE-GAN model in computer vision. Besides, we integrate two attentional mechanisms with GAN to get the essential regions of interest in a video, focused on enhancing the visual implementation of the human motion in the generated output. We have considered quantitative and qualitative experiments, including comparisons with other state-of-the-arts for evaluation. Our results indicate that our model enhances performance compared with other models and performs favorably under different quantitive metrics PSNR, SSIM, LPIPS, and FVD.Recently, mimicking biologically inspired learning in generative models based on SNNs has been shown their effectiveness in different applications. SNNs are the third generation of neural networks, in which neurons communicate through binary signals known as spikes. Since SNNs are more energy-efficient than DNNs. Moreover, DNN models have been vulnerable to small adversarial perturbations that cause misclassification of legitimate images. This dissertation shows the proposed ``VAE-Sleep'' that combines ideas from VAE and the sleep mechanism leveraging the advantages of deep and spiking neural networks (DNN--SNN).On top of that, we present ``Defense–VAE–Sleep'' that extended work of ``VAE-Sleep'' model used to purge adversarial perturbations from contaminated images. We demonstrate the benefit of sleep in improving the generalization performance of the traditional VAE when the testing data differ in specific ways even by a small amount from the training data. We conduct extensive experiments, including comparisons with the state–of–the–art on different datasets.

The global increase in internet usage requires an upgrade of the existing infrastruc- ture. Lasers are a key proponent to improving existing systems, and engineering better gain materials aids in this effort. (InGa)As is the leading material in this field for 1.55 μm communication wavelengths, but can be improved on by changing the substrate from InP to GaAs. Another improvement would be reducing the losses due to Auger recombination. (InGa)(BiAs) is suggested to alleviate many of these issues, as it can be grown on a GaAs substrate and is capable of decreased Auger recombination. By analyzing prospective alloys (and existing ones) using spatial electron localization, a superior candidate for industrial use can be suggested. The localization captures the disorder introduced by alloying and can be associated with material properties such as the gain characteristics and photoluminescence linewidths. These properties are important factors in determining a successor. The subject of two-dimensional materials is another topic which has shown promise in various applica- tions. Examples include flexible, transparent, and miniaturized electronics. Recent research done by Al Balushi et al. suggests that GaN may be stabilized in a two-dimensional sys- tem. By extending the material modelling approach from the telecommunication application to this system, we were able to show which III-V isoelectronic elements can be substituted into GaN. This two-dimensional system may be the only candidate capable of spanning the visible spectrum. We found Phosphorus to be the strongest candidate for decreasing the band gap. / Thesis / Master of Applied Science (MASc)