Fig. 4. The Application of the Network
When the label has the multi-attribute[4], we can
use this network to generate different things. My another paper is about
multi-attribute label.
Conclusion
1.The network achieves the intended function through inverse function.
The abstract network can classify and regress, the concrete network can
generate input from concept or label.
2.We can change the input to any form by encoder and then change it back
by decoder through inverse function. The concrete network can be seen as
the memory stored by the parameters. Lethe is that when new knowledge
input, the training process makes the parameters change.
References
- Ian Goodfellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT
Press, 2016,pp 67-69
- Andrew L, Maas, Awni Y, Hannum and Andrew Y. Ng, “Rectified
Nonlinearities Improve Neural Network Acoustic Models”, ICML, 2013.
- Tensorflow Tutorials and Apis,https://tensorflow.google.cn/learn last accessed 2020/3/20
- Jinxin Wei, Qunying Ren “Multi-attribute Recognition,the Key to
Universal Neural Network”. unpublished