Please enable JavaScript.
Coggle requires JavaScript to display documents.
State of The Art Deepning - Coggle Diagram
State of The Art Deepning
MODELS COMPRESSION
Performance Evaluation of Deep Learning Compilers for Edge Inference
Link to document
:date: 2021
Model-based Weight Quantization for Convolutional Neural Network Compression
Link to document
:date: 2021
TreeNet: A Hierarchical Deep Learning Model to Facilitate Edge Intelligence for Resource-Constrained Devices
Link to document
:date: 2021
Random sketch learning for deep neural networks in edge computing
Link to document
:date: 2021
E2CNNs: Ensembles of Convolutional Neural Networks to Improve Robustness Against Memory Errors in Edge-Computing Devices
Link to document
:date: 2021
Multi-Model Inference Acceleration on Embedded Multi-Core Processors
Link to document
:date: 2020
Compressing and Mapping Deep Neural Networks on Edge Computing Systems
Link to document
:date: 2021
Compressing NN
Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks
Computation-Performance Optimization of Convolutional Neural Networks With Redundant Filter Removal
Deep Model Compression and Architecture Optimization for Embedded Systems: A Survey
Differential Evolution Based Layer-Wise Weight Pruning for Compressing Deep Neural Networks
iRDA Method for Sparse Convolutional Neural Network
N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning
Optimizing GPU System for Efficient Resource Utilization of General Purpose Applications in a Multitasking Environment
Structured Multi-Hashing for Model Compression
TERNARYHYBRIDNEURAL-TREENETWORKS FORHIGHLYCONSTRAINEDIOT APPLICATIONS
Training with Quantization Noise for Extreme Model Compression
A Multi-Neural Network Acceleration Architecture
:date: 2020
Fast and Scalable In-memory Deep Multitask Learning via Neural Weight Virtualization
:date: 2020
GPU Scheduling forMulti-DNN Real-Time Inference
:date: 2019
Mobile-Cloud Cooperative Deep Learning Platform for Mixed Reality Applications
:date: 2021
:warning:
Enabling Deep Intelligence on Embedded Systems
:warning:
Deploying Deep Neural Networks in the Embedded Space
:warning:
MULTI DNN
Merging Deep Neural Networks for Mobile Devices
Link to document
:date: 2018
Multi-objective Recurrent Neural Networks Optimization for the Edge – a Quantization-based Approach
Link to document
:date: 2021
:warning:
Multi-model inference on the edge
Link to document
:date: 2020
MemA: Fast Inference of Multiple Deep Models
Link to document
:date: 2021
Masa: Responsive Multi-DNN Inference on the Edge
Link to document
:date: 2021
An online guided Tuning Approach to run CNN Pipelines on Edge Devices
Link to document
:date: 2021
:warning:
Multi-objective Precision Optimization of Deep Neural Networks for Edge Devices
Link to document
:date: 2019
:warning:
Multi-inference on the Edge: Scheduling Networks with Limited Available Memory
Link to document
:date: 2021
Proximu$: Efficiently Scaling DNN Inference in multi-core CPUs through Near-Cache Compute
Link to document
:date: 2020