Loading...
Search for:
mazloomian--alborz
0.097 seconds
Inferring Signaling Pathways from RNAi Data Using Machine Learning
,
M.Sc. Thesis
Sharif University of Technology
;
Beigy, Hamid
(Supervisor)
Abstract
One of the standing problems in Molecular Biology and Bioinformatics is uncovering signaling pathways. Discovering the causes of many cancer-like diseases and developing better treatments for them, requires a better understanding of the behavior of cellular processes. Understanding signaling pathways can help to realize cellular processes. Due to the fast increase of possible signaling pathways when the number of components increases, the problem seems to have an inherent complexity. One of the recent methods for generating data relating to such networks is RNA interference technique. In this thesis we use data which are provided by this method. We propose two methods to infer signaling...
Inferring signaling pathways using interventional data
, Article Intelligent Data Analysis ; Volume 17, Issue 2 , April , 2013 , Pages 295-308 ; 1088467X (ISSN) ; Beigy, H ; Sharif University of Technology
2013
Abstract
Studying biological networks helps to gain a better understanding of cellular behaviors. One of the prominent models to study complex interactions in biological networks is the Nested Effects Model (NEM). Based on the Nested Effects Model, we propose two methods for inferring signaling pathways from interventional data. In the first method, we search the space of all feasible solutions with an evolutionary approach to maximize a standard Bayesian score. In the second method, sub-models are constructed with informative features and then combined using an averaging method to make the analysis of larger networks computationally possible. We tested our proposed methods in various noise levels on...
Evaluation of the Impact of Activation Functions on the Fault Tolerance of Deep Neural Networks
, M.Sc. Thesis Sharif University of Technology ; Hessabi, Shaahin (Supervisor)
Abstract
Deep neural networks, as one of the main approaches in machine learning, play a crucial role in analyzing complex data and identifying hidden patterns. However, significant challenges such as high sensitivity to input errors, noise, and minor data variations still persist. One of the key strategies to address these challenges and improve the stability and accuracy of neural networks is the proper and optimal use of activation functions. Activation functions allow networks to process data non-linearly and extract more complex features from the data. However, an incorrect choice of activation function or suboptimal tuning can reduce the network's performance and make it more sensitive to input...