AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Constrained deep neural network architecture search for IoT devices accounting for hardware calibration

Florian Scheidegger, Luca Benini, Costas Bekas, A. Cristiano I. Malossi

NeurIPS 2019 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Search narrow architecture spaces for floating-point models under the same memory constraintsEstablished IoT model · CIFAR-10accuracy: 70.64% -> 74.87%Improved
Run models using 16-bit half types (ablation)Narrow-space search · CIFAR-10accuracy: 74.87% -> 82.07%Improved
Use model-optimized IEEE 754 reduced types (ablation)Narrow-space search · CIFAR-10accuracy: 82.07% -> 83.45%Improved
Run with half precision (ablation)Trained models in the IoT-relevant domain under a given memory constraint · CIFAR-10accuracy: over 7% pointsImproved
Choose an individual reduced-precision format for each model (ablation)Trained models in the IoT-relevant domain under a given memory constraint · CIFAR-10accuracy: over 1% points furtherImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy