Representation Search through Generate and Test

Learning representations from data is one of the fundamental problems of artificial intelligence and machine learning. Many different approaches exist for learning representations, but what constitutes a good representation is not yet well understood. In this work, we view the problem of representation learning as one of learning features (e.g., hidden units of neural networks) such that performance of the underlying base system continually improves. We study an important case where learning is done fully online (i.e., on an example-by-example basis) from an unending stream of data. In the presence of an unending stream of data, the computational cost of the learning element should not grow with time and cannot be much more than that of the performance element. Few methods can be used effectively in this case. We show that a search approach to representation learning can naturally fit with this setting. In this approach good representations are searched by generating different features and then testing them for utility. We develop new representation-search methods and show that the generate-and-test approach can be utilized in a simple and effective way for learning representations. Our methods are fully online and add only a small fraction to the overall computation. They constitute an important step toward effective and inexpensive solutions to representation learning problems.

[1]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[2]  Richard S. Sutton,et al.  Online Learning with Random Representations , 1993, ICML.

[3]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[4]  Ron Kohavi,et al.  Irrelevant Features and the Subset Selection Problem , 1994, ICML.

[5]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[6]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[7]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.

[8]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[9]  Peter Vamplew,et al.  Global Versus Local Constructive Function Approximation for On-Line Reinforcement Learning , 2005, Australian Conference on Artificial Intelligence.

[10]  Shimon Whiteson,et al.  Evolutionary Function Approximation for Reinforcement Learning , 2006, J. Mach. Learn. Res..

[11]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[12]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[13]  Geoffrey E. Hinton Learning multiple layers of representation , 2007, Trends in Cognitive Sciences.

[14]  Yoshua Bengio,et al.  Scaling learning algorithms towards AI , 2007 .

[15]  Shimon Whiteson,et al.  Adaptive Representations for Reinforcement Learning , 2010, Studies in Computational Intelligence.

[16]  Patrick M. Pilarski,et al.  Tuning-free step-size adaptation , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).