Neural Network Quine

Self-replication is a key aspect of biological life that has been largely overlooked in Artificial Intelligence systems. Here we describe how to build and train self-replicating neural networks. The network replicates itself by learning to output its own weights. The network is designed using a loss function that can be optimized with either gradient-based or non-gradient-based methods. We also describe a method we call regeneration to train the network without explicit optimization, by injecting the network with predictions of its own parameters. The best solution for a self-replicating network was found by alternating between regeneration and optimization steps. Finally, we describe a design for a self-replicating neural network that can solve an auxiliary task such as MNIST image classification. We observe that there is a trade-off between the network's ability to classify images and its ability to replicate, but training is biased towards increasing its specialization at image classification at the expense of replication. This is analogous to the trade-off between reproduction and other tasks observed in nature. We suggest that a self-replication mechanism for artificial intelligence is useful because it introduces the possibility of continual improvement through natural selection.

[1]  Marcin Andrychowicz,et al.  Learning to learn by gradient descent by gradient descent , 2016, NIPS.

[2]  Misha Denil,et al.  Predicting Parameters in Deep Learning , 2014 .

[3]  Sepp Hochreiter,et al.  Self-Normalizing Neural Networks , 2017, NIPS.

[4]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[5]  Douglas R. Hofstadter,et al.  Godel, Escher, Bach: An Eternal Golden Braid. , 1980 .

[6]  Benjamin Recht,et al.  Random Features for Large-Scale Kernel Machines , 2007, NIPS.

[7]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Silvio Savarese,et al.  Learning to Track at 100 FPS with Deep Regression Networks , 2016, ECCV.

[9]  W. B. Johnson,et al.  Extensions of Lipschitz mappings into Hilbert space , 1984 .

[10]  L. Penrose,et al.  Self-Reproducing Machines , 1959 .

[11]  Douglas R. Hofstadter,et al.  Godel, Escher, Bach: An Eternal Golden Braid , 1981 .

[12]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[13]  Jarle Breivik,et al.  Self-Organization of Template-Replicating Polymers and the Spontaneous Rise of Genetic Information , 2001, Entropy.

[14]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[15]  David J. Pine,et al.  Self-replication of information-bearing nanoscale patterns , 2011, Nature.

[16]  Xi Chen,et al.  Evolution Strategies as a Scalable Alternative to Reinforcement Learning , 2017, ArXiv.

[17]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[18]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[19]  Hod Lipson,et al.  A Universal Framework for Analysis of Self-Replication Phenomena , 2009, Entropy.

[20]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[21]  Hod Lipson,et al.  Robotics: Self-reproducing machines , 2005, Nature.

[22]  Kenneth O. Stanley,et al.  Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning , 2017, ArXiv.

[23]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[24]  Navdeep Jaitly,et al.  Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[25]  Quoc V. Le,et al.  HyperNetworks , 2016, ICLR.

[26]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Tom Schaul,et al.  StarCraft II: A New Challenge for Reinforcement Learning , 2017, ArXiv.

[28]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[29]  Kenneth O. Stanley.  A Hypercube-Based Indirect Encoding for Evolving Large-Scale Neural Networks , 2009 .

[30]  Qiang Yang,et al.  Lifelong Machine Learning Systems: Beyond Learning Algorithms , 2013, AAAI Spring Symposium: Lifelong Machine Learning.

[31]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[32]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[33]  Jürgen Schmidhuber,et al.  Learning to Control Fast-Weight Memories: An Alternative to Dynamic Recurrent Networks , 1992, Neural Computation.

[34]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.