Description: 实现了卷积受限玻尔兹曼机(深度学习的一个重要算法),包括C++和matlab版本-Restricted Boltzmann realized convolution machine (depth study of an important algorithm), including C++ and matlab version Platform: |
Size: 4290560 |
Author:张纯化 |
Hits:
Description: 针对各种机器学习,深度学习领域的一个matlab工具包-A machine learning library focused on deep learning.Following algorithms and models are provided along with some static utility classes:
- Naive Bayes, Linear Regression, Logistic Regression, Softmax Regression, Linear Support Vector Machine, Non-Linear Support Vector Machine (with RBF kernel),
Feed-forward Neural Network, Embedding Neural Network, Convolutional Neural Network, Sparse Autoencoders, Denoising Autoencoders,
Contractive Autoencoders, Stacked Sparse Autoencoders, Self-Taught Learner and Restricted Boltzmann Machines are tested with this version.
- Rest of the methods are not tested hence not supplied and the progress is as follows:
+ Deep Belief Nets with Restricted Boltzmann Machines (not tested)
+ Bayes Nets (tested- refactoring)
+ Hidden Markov Models (tested- refactoring)
+ Conditional Random Fields (work in progress) Platform: |
Size: 346112 |
Author:zhjhe |
Hits:
Description: 一本关于深度架构学习算法,尤其是用来构造更深层模型的非监督学习的单层模型。(Theoretical results suggest that in order to learn the kind of com-
plicated functions that can represent high-level abstractions (e.g., in
vision, language, and other AI-level tasks), one may need deep architec-
tures. Deep architectures are composed of multiple levels of non-linear
operations, such as in neural nets with many hidden layers or in com-
plicated propositional formulae re-using many sub-formulae. Searching
the parameter space of deep architectures is a difficult task, but learning
algorithms such as those for Deep Belief Networks have recently been
proposed to tackle this problem with notable success, beating the state-
of-the-art in certain areas. This monograph discusses the motivations
and principles regarding learning algorithms for deep architectures, in
particular those exploiting as building blocks unsupervised learning of
single-layer models such as Restricted Boltzmann Machines, used to
construct deeper models such as Deep Belief Networks.) Platform: |
Size: 1017856 |
Author:cserhz
|
Hits:
Description: 有限玻尔兹曼机、深度置信网的Matlab实现,用mnist数据进行验证,对理解深度学习原理有帮助。(A Finite Boltzmann machine and deep belief network are implemented in MATLAB and verified with MNIST data. It is helpful to understand the principle of deep learning.) Platform: |
Size: 4786176 |
Author:mujckie |
Hits: