While evolutionary algorithms (EAs) have long offered an alternative approach to optimization, in recent years backpropagation through stochastic gradient descent (SGD) has come to dominate the fields of neural network optimization and deep learning. One hypothesis for the absence of EAs in deep learning is that modern neural networks have become so high dimensional that evolution with its inexact gradient cannot match the exact gradient calculations of backpropagation. Furthermore, the evaluation of a single individual in evolution on the big data sets now prevalent in deep learning would present a prohibitive obstacle towards efficient optimization. This paper challenges these views, suggesting that EAs can be made to run significantly faster than previously thought by evaluating individuals only on a small number of training examples per generation. Surprisingly, using this approach with only a simple EA (called the limited evaluation EA or LEEA) is competitive with the performance of the state-of-the-art SGD variant RMSProp on several benchmarks with neural networks with over 1,000 weights. More investigation is warranted, but these initial results suggest the possibility that EAs could be the first viable training alternative for deep learning outside of SGD, thereby opening up deep learning to all the tools of evolutionary computation.

Legged robots can potentially venture beyond the limits of wheeled vehicles. While creating controllers for such robots by hand is possible, evolutionary algorithms are an alternative that can reduce the burden of hand-crafting robotic controllers. Although major evolutionary approaches to legged locomotion can generate oscillations through popular techniques such as continuous time recurrent neural networks (CTRNNs) or sinusoidal input, they typically face a challenge in maintaining long-term stability. The aim of this paper is to address this challenge by introducing an effective alternative based on a new type of neuron called a singleunit pattern generator (SUPG). The SUPG, which is indirectly encoded by a compositional pattern producing network (CPPN) evolved by HyperNEAT, produces a flexible temporal activation pattern that can be reset and repeated at any time through an explicit trigger input, thereby allowing it to dynamically recalibrate over time to maintain stability. The SUPG approach, which is compared to CTRNNs and sinusoidal input, is shown to produce natural-looking gaits that exhibit superior stability over time, thereby providing a new alternative for evolving oscillatory locomotion.

Unlike unsupervised approaches such as autoencoders that learn to reconstruct their inputs, this paper introduces an alternative approach to unsupervised feature learning called divergent discriminative feature accumulation (DDFA) that instead continually accumulates features that make novel discriminations among the training set. Thus DDFA features are inherently discriminative from the start even though they are trained without knowledge of the ultimate classification problem. Interestingly, DDFA also continues to add new features indefinitely (so it does not depend on a hidden layer size), is not based on minimizing error, and is inherently divergent instead of convergent, thereby providing a unique direction of research for unsupervised feature learning. In this paper the quality of its learned features is demonstrated on the MNIST dataset, where its performance confirms that indeed DDFA is a viable technique for learning useful features.

No abstract

This paper considers an obfuscation scheme designed around runtime generated self-modifying code and irreducible loops, both of which are notoriously difficult to reason about. This leads to a mechanism for both source and binary code that increase resistance to static analysis as well as dynamic analysis. By making use of the fact that static analysis of self-modifying code has limits in decidability as per Rice's theorem, and that transformation of irreducible loops to reducible ones using techniques such as node-splitting or introduction of variables can have a quadratic complexity increase on the size of the control-flow graph. Our construction looks at turning an algorithm into the lowest abstraction level with multi-input logic gates, to evaluate the most generic perspective on the scheme though it is applicable to any control-flow graph. A final benefit is that although complicated and naturally inter-related, the different ideas could be applied separately.