Difference between revisions of "Deep Learning"
| Line 15: | Line 15: | ||
* [[ResNet-50]] | * [[ResNet-50]] | ||
* [http://medium.com/@gokul_uf/the-anatomy-of-deep-learning-frameworks-46e2a7af5e47 The Anatomy of Deep Learning Frameworks | Gokula Krishnan Santhanam] | * [http://medium.com/@gokul_uf/the-anatomy-of-deep-learning-frameworks-46e2a7af5e47 The Anatomy of Deep Learning Frameworks | Gokula Krishnan Santhanam] | ||
| + | * [[Hierarchical Temporal Memory (HTM)]] | ||
http://www.global-engage.com/wp-content/uploads/2018/01/Deep-Learning-blog.png | http://www.global-engage.com/wp-content/uploads/2018/01/Deep-Learning-blog.png | ||
Revision as of 09:50, 3 February 2019
YouTube search... ...Google search
- Other Challenges of Machine Learning
- Deep Neural Network (DNN)
- (Deep) Convolutional Neural Network (DCNN/CNN)
- (Deep) Residual Network (DRN) - ResNet
- Deep Belief Network (DBN)
- ResNet-50
- The Anatomy of Deep Learning Frameworks | Gokula Krishnan Santhanam
- Hierarchical Temporal Memory (HTM)
Deep learning models are vaguely inspired by information processing and communication patterns in biological nervous systems yet have various differences from the structural and functional properties of biological brains, which make them incompatible with neuroscience evidences. “Deep Learning is an algorithm which has no theoretical limitations of what it can learn; the more data you give and the more computational time you provide, the better it is” Learning Multiple Layers of Representation | Geoffrey Hinton
