Deep learning neural network tools for proteomics
نویسندگان
چکیده
منابع مشابه
Reinforced backpropagation for deep neural network learning
Standard error backpropagation is used in almost all modern deep network training. However, it typically suffers from proliferation of saddle points in high-dimensional parameter space. Therefore, it is highly desirable to design an efficient algorithm to escape from these saddle points and reach a good parameter region of better generalization capabilities, especially based on rough insights a...
متن کاملProteomics Analysis of FLT3-ITD Mutation in Acute Myeloid Leukemia Using Deep Learning Neural Network
Deep Learning can significantly benefit cancer proteomics and genomics. In this study, we attempt to determine a set of critical proteins that are associated with the FLT3-ITD mutation in newly-diagnosed acute myeloid leukemia patients. A Deep Learning network consisting of autoencoders forming a hierarchical model from which high-level features are extracted without labeled training data. Dime...
متن کاملCompressed Learning: A Deep Neural Network Approach
This work presents a novel deep learning approach to Compressed-Learning. Jointly optimizing the sensing and inference operators. Outperforming state-of-the-art CL methods on MNIST and CIFAR10. Extendible to numerous CL applications. The research leading to these results has received funding from the European Research Council under European Union's Seventh Framework Program, ERC Grant agre...
متن کاملArtificial Intelligence and Neural Network Based Tools for Cooperative Learning
Introduction Learning modalities System architecture Agent specification Tutor agent Tutor assistant agent Learner personal agent Steps towards a user comprehensive model Conclusions Acknowledgements References
متن کاملAn Overview of Convolutional Neural Network Architectures for Deep Learning
Since AlexNet was developed and applied to the ImageNet classi cation competition in 2012 [1], the quantity of research on convolutional networks for deep learning applications has increased remarkably. In 2015, the top 5 classi cation error was reduced to 3.57%, with Microsoft's Residual Network [2]. The previous top 5 classi cation error was 6.67%, achieved by GoogLeNet [3]. In recent years, ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Cell Reports Methods
سال: 2021
ISSN: 2667-2375
DOI: 10.1016/j.crmeth.2021.100003