Electrical and Computer Engineering
Permanent URI for this collection
Browse
Browsing Electrical and Computer Engineering by Subject "Artificial intelligence"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access Deep Unsupervised Learning for Network Resource Allocation Problems with Convex and Non-Convex Constraints(2023-03-28) Alizadeh, Mehrazin; Tabassum, HinaDeep neural networks (DNNs) are currently emerging as a potential solution to solve NP-hard wireless resource allocation problems. However, in the presence of intricate constraints, e.g., users' quality-of-service (QoS) constraints or base station quota, guaranteeing constraint satisfaction becomes a fundamental challenge. In this thesis, I propose a novel unsupervised learning framework to solve the classical power control and user assignment problem in a multi-user interference channel, where the objective is to maximize the network sum-rate with QoS, power budget, and base station quota constraints. The proposed method utilizes a differentiable projection function, defined both implicitly and explicitly, to project the output of the DNN to the feasible set of the problem. Extensive simulations depict that the proposed DNN solutions not only improve the achievable data rate, but also achieve zero constraint violation probability, compared to the existing DNNs, and also outperform the optimization-based benchmarks in computation time.Item Open Access Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images(2022-12-14) Maleky, Ali; Brown, Michael S.Image noise modeling is a long-standing problem with many applications in computer vision. Early attempts that propose simple models, such as signal-independent additive white Gaussian noise or the heteroscedastic Gaussian noise model (a.k.a., camera noise level function) are not sufficient to learn the complex behavior of the camera sensor noise. Recently, more complex learning-based models have been proposed that yield better results in noise synthesis and downstream tasks, such as denoising. However, their dependence on supervised data (i.e., paired clean images) is a limiting factor given the challenges in producing ground-truth images. This paper proposes a framework for training a noise model and a denoiser simultaneously while relying only on pairs of noisy images rather than noisy/clean paired image data. We apply this framework to the training of the Noise Flow architecture. The noise synthesis and density estimation results show that our framework outperforms previous signal-processing-based noise models and is on par with its supervised counterpart. The trained denoiser is also shown to significantly improve upon both supervised and weakly supervised baseline denoising approaches. The results indicate that the joint training of a denoiser and a noise model yields significant improvements in the denoiser.