Browse > Methodology > AutoML > Neural Architecture Search

Neural Architecture Search

138 papers with code ยท Methodology
Subtask of AutoML

Leaderboards

Latest papers without code

Training Large Neural Networks with Constant Memory using a New Execution Algorithm

13 Feb 2020

To overcome the bandwidth issues of shuttling parameters to and from EPS, the model is executed a layer at a time across many micro-batches instead of the conventional method of minibatches over whole model.

DISTRIBUTED OPTIMIZATION NEURAL ARCHITECTURE SEARCH

Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator

11 Feb 2020

We automate HW-CNN codesign using NAS by including parameters from both the CNN model and the HW accelerator, and we jointly search for the best model-accelerator pair that boosts accuracy and efficiency.

IMAGE CLASSIFICATION MULTIOBJECTIVE OPTIMIZATION NEURAL ARCHITECTURE SEARCH

Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks

10 Feb 2020

Neural Architecture Search (NAS) has demonstrated its power on various AI accelerating platforms such as Field Programmable Gate Arrays (FPGAs) and Graphic Processing Units (GPUs).

NEURAL ARCHITECTURE SEARCH

NASS: Optimizing Secure Inference via Neural Architecture Search

30 Jan 2020

Due to increasing privacy concerns, neural network (NN) based secure inference (SI) schemes that simultaneously hide the client inputs and server models attract major research interests.

NEURAL ARCHITECTURE SEARCH

Bayesian Neural Architecture Search using A Training-Free Performance Metric

29 Jan 2020

Recurrent neural networks (RNNs) are a powerful approach for time series prediction.

NEURAL ARCHITECTURE SEARCH TIME SERIES TIME SERIES PREDICTION

Multi-objective Neural Architecture Search via Non-stationary Policy Gradient

23 Jan 2020

Despite recent progress, the problem of approximating the full Pareto front accurately and efficiently remains challenging.

NEURAL ARCHITECTURE SEARCH

Efficient Neural Architecture Search: A Broad Version

18 Jan 2020

In this paper, we propose a Broad version for ENAS (BENAS) to solve the above issue, by learning broad architecture whose propagation speed is fast with reinforcement learning and parameter sharing used in ENAS, thereby achieving a higher search efficiency.

NEURAL ARCHITECTURE SEARCH

ENAS U-Net: Evolutionary Neural Architecture Search for Retinal Vessel Segmentation

18 Jan 2020

We propose a specific search space based on encoder-decoder framework and apply neural architecture search (NAS) to retinal vessel segmentation.

NEURAL ARCHITECTURE SEARCH RETINAL VESSEL SEGMENTATION

Latency-Aware Differentiable Neural Architecture Search

17 Jan 2020

The core of latency prediction is to encode each network architecture and feed it into a multi-layer regressor, with the training data being collected from randomly sampling a number of architectures and evaluating them on the hardware.

NEURAL ARCHITECTURE SEARCH