Carlos Perez is a software developer presently writing a book on "Design Patterns for Deep Learning". This is where he sources his ideas for his blog posts.
If you are interested in finding out how Deep Learning can help you in your work, please feel to leave your email at: www.intuitionmachine.com or join the discussion in Facebook: www.facebook.com/groups/deeplearningpatterns/.
This article is just a reflection of my current understanding of the language of Deep Learning Meta Meta-Model. That’s definitely a mouth full, so to make life simpler for everyone, I just call this the Deep Learning Canonical Patterns.
This post discusses a variety of contemporary Deep Meta Learning methods, in which meta-data is manipulated to generate simulated architectures. Current meta-learning capabilities involve either support for search for architectures or networks inside networks.
In short, you reach different resting placing with different SGD algorithms. That is, different SGDs just give you differing convergence rates due to different strategies, but we do expect that they all end up at the same results!
The most advanced kind of Deep Learning system will involve multiple neural networks that either cooperate or compete to solve problems. The core problem of a multi-agent approach is how to control its behavior.
Deep Learning systems exhibit behavior that appears biological despite not being based on biological material. It so happens that humanity has luckily stumbled upon Artificial Intuition in the form of Deep Learning.
This post is a rebuttal to a recent article suggesting that neural networks cannot be applied to natural language given that language is not a produced as a result of continuous function. The post delves into some additional points on deep learning as well.
This post covers the emergence of Game Theoretic concepts in the design of newer deep learning architectures. Deep learning systems need to be adaptive to imperfect knowledge and coordinating systems, 2 areas with which game theory can help.