FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search

Efficient Neural Architecture Search via Parameter Sharing

We propose Efficient Neural Architecture Search (ENAS), a fast and inexpensive approach for automatic model design. In ENAS, a controller discovers neural network architectures by searching for an optimal subgraph within a large computational graph. The controller is trained with policy gradient to select a subgraph that maximizes the expected reward on a validation set. Meanwhile the model cor...

Architecture-Dependent Loop Scheduling via Communication-Sensitive Remapping

In this paper, we propose a novel efficient technique called cyclo-compaction scheduling, taking into account the data transmission delays and loop carried dependency associated with specific target architectures. This technique uses the retiming technique (loop pipelining), implicitly applied, and a task remapping to appropriate processors in order to compact the schedule length and improve th...

Gradient-free Policy Architecture Search and Adaptation

We develop a method for policy architecture search and adaptation via gradient-free optimization which can learn to perform autonomous driving tasks. By learning from both demonstration and environmental reward we develop a model that can learn with relatively few early catastrophic failures. We first learn an architecture of appropriate complexity to perceive aspects of world state relevant to...

Differentiable Neural Network Architecture Search

The successes of deep learning in recent years has been fueled by the development of innovative new neural network architectures. However, the design of a neural network architecture remains a difficult problem, requiring significant human expertise as well as computational resources. In this paper, we propose a method for transforming a discrete neural network architecture space into a continu...

Harmony Search Based Parameter Ensemble Adaptation for Differential Evolution