Learn More
Many deep neural networks trained on natural images exhibit a curious phenomenon in common: on the first layer they learn features similar to Gabor filters and color blobs. Such first-layer features appear not to be specific to a particular dataset or task, but general in that they are applicable to many datasets and tasks. Features must eventually(More)
Animals sustain the ability to operate after injury by creating qualitatively different compensatory behaviors. Although such robustness would be desirable in engineered systems, most machines fail in the face of unexpected damage. We describe a robot that can recover from such change autonomously, through continuous self-modeling. A four-legged machine(More)
This paper describes an optimization-based algorithm for reconstructing a 3D model from a single, inaccurate, 2D edge-vertex graph. The graph, which serves as input for the reconstruction process, is obtained from an inaccurate free-hand sketch of a 3D wireframe object. Compared with traditional reconstruction methods based on line labelling, the proposed(More)
Recent years have produced great advances in training large, deep neural networks (DNNs), including notable successes in training convolutional neural networks (convnets) to recognize natural images. However, our understanding of how these models work, especially what computations they perform at intermediate layers, has lagged behind. Progress in the field(More)
The field of modular self-reconfigurable robotic systems addresses the design, fabrication, motion planning, and control of autonomous kinematic machines with variable morphology. Modular self-reconfigurable systems have the promise of making significant technological advances to the field of robotics in general. Their promise of high versatility, high(More)
An important key to reconstructing a three-dimensional object depicted by a two-dimensional line drawing projection is face identification. Identification of edge circuits in a 2D projection corresponding to actual faces of a 3D object becomes complex when the projected object is in wireframe representation. This representation is commonly encountered in(More)
We present a coevolutionary algorithm for inferring the topology and parameters of a wide range of hidden nonlinear systems with a minimum of experimentation on the target system. The algorithm synthesizes an explicit model directly from the observed data produced by intelligently generated tests. The algorithm is composed of two coevolving populations. One(More)
A central biological question is how natural organisms are so evolvable (capable of quickly adapting to new environments). A key driver of evolvability is the widespread modularity of biological networks--their organization as functional, sparsely connected subunits--but there is no consensus regarding why modularity itself evolved. Although most hypotheses(More)
We propose a multi-objective method for avoiding premature convergence in evolutionary algorithms, and demonstrate a three-fold performance improvement over comparable methods. Previous research has shown that partitioning an evolving population into age groups can greatly improve the ability to identify global optima and avoid converging to local optima.(More)