~hackernoon | Bookmarks (20)

clear filters

neural-networks ×

Comparative Analysis: Learned Heuristics vs. WalkSAT in SAT Problem Solving

hackernoon.com

Dive deeper into the supplementary materials providing insights into intra-episode behavior, generalization across small and hard...
Dive deeper into the supplementary materials providing insights into intra-episode behavior, generalization across small and hard instances, and comparative analysis of learned SAT heuristics against the WalkSAT algorithm. Explore detailed tables, plots, and performance metrics for a comprehensive understanding of the evaluation outcomes. TLDR for Supplementary Materials: The supplementary materials offer detailed analysis on intra-episode behavior, generalization capabilities on small and hard instances, and...

deep-learning heuristics-evaluation learned-sat-heuristics local-search-heuristics neural-networks
1
Assessing the Justification for Integrating Deep Learning in Combinatorial Optimization

hackernoon.com

This summary highlights the importance of conducting thorough comparisons between deep learning-integrated heuristics and classical heuristics...
This summary highlights the importance of conducting thorough comparisons between deep learning-integrated heuristics and classical heuristics in combinatorial optimization. It emphasizes the need to articulate both strengths and weaknesses to guide research investments and justify the integration of deep learning architectures.

deep-learning heuristic-algorithms heuristics-evaluation local-search-heuristics neural-networks
1
Understanding the Limitations of GNNSAT in SAT Heuristic Optimization

hackernoon.com

This article explores the performance and scalability challenges of GNNSAT, a learned SAT heuristic, compared to...
This article explores the performance and scalability challenges of GNNSAT, a learned SAT heuristic, compared to SoftTabu. Through a detailed evaluation on SAT problem distributions, it reveals insights into the limitations and potential improvements of learned algorithms in combinatorial optimization contexts.

deep-learning graph-neural-networks local-search-algorithms local-search-heuristics neural-networks
1
Analyzing Learned Heuristics for Max-Cut Optimization

hackernoon.com

This article delves into the evaluation of learned heuristics like S2V-DQN and ECO-DQN against traditional heuristics...
This article delves into the evaluation of learned heuristics like S2V-DQN and ECO-DQN against traditional heuristics like Tabu Search in the context of Max-Cut optimization. It analyzes their performance, generalization to unseen graph types, and scalability to harder instances, shedding light on the efficacy of machine learning approaches in solving combinatorial optimization problems.

deep-learning local-search-heuristics max-cut-optimization neural-networks performance-benchmarking
1
Exploring Classical and Learned Local Search Heuristics for Combinatorial Optimization

hackernoon.com

This section delves into the realm of local search heuristics in combinatorial optimization, covering classical heuristics...
This section delves into the realm of local search heuristics in combinatorial optimization, covering classical heuristics and advanced learned heuristics like ECO-DQN and GNN-SAT. It highlights the evolution of machine learning integration in solving CO problems, showcasing the advancements in algorithmic approaches.

deep-learning graph-neural-networks local-search-heuristics neural-networks reinforcement-learning
1
Unveiling the Limits of Learned Local Search Heuristics: Are You the Mightiest of the Meek?

hackernoon.com

This abstract outlines the challenges encountered in evaluating neural network-local search heuristics hybrids for combinatorial optimization....
This abstract outlines the challenges encountered in evaluating neural network-local search heuristics hybrids for combinatorial optimization. It discusses limitations in algorithm performance evaluation, generalizability, and the impact of instance selection bias, offering insights that challenge prevailing assumptions in the field.

deep-learning hackernoon-top-story hybrid-algorithms instance-selection-bias local-search-heuristics
1
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Experimental Results

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Opportunities

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Motivation

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Experiments

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Conclusion & References

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Hardware Details

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Arithmetic Intensity

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
Modeling Workload Interference

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
Proble Formulation: Two-Phase Tuning

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Predictor Analysis

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Architecture Overview

hackernoon.com

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference...
This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

edge-devices fine-tuning neural-network-inference neural-networks on-device-hardware
1
A Deep Dive Into Semantic Segmentation Evaluation Metrics

hackernoon.com

Semantic segmentation is an area of computer vision that specialises in dividing an image into regions...
Semantic segmentation is an area of computer vision that specialises in dividing an image into regions based on pixel characteristics.

computer-vision metrics neural-networks pixels relative-volume
1
82 Stories To Learn About Neural Networks

hackernoon.com

artificial-intelligence deep-learning learn learn-neural-networks machine-learning
1
QLoRA: Fine-Tuning Your LLMs With a Single GPU

hackernoon.com

To fine-tune a LLAMA 65 billion parameter model, we need 780 GB of GPU memory. That...
To fine-tune a LLAMA 65 billion parameter model, we need 780 GB of GPU memory. That is about 16 A40 GPUs. The solution lies with QLoRA where Q stands for Quantisation.

artificial-intelligence deep-learning generative-ai gpu lora
1

~hackernoon | Bookmarks (20)

Tags

Domains

Comparative Analysis: Learned Heuristics vs. WalkSAT in SAT Problem Solving

Assessing the Justification for Integrating Deep Learning in Combinatorial Optimization

Understanding the Limitations of GNNSAT in SAT Heuristic Optimization

Analyzing Learned Heuristics for Max-Cut Optimization

Exploring Classical and Learned Local Search Heuristics for Combinatorial Optimization

Unveiling the Limits of Learned Local Search Heuristics: Are You the Mightiest of the Meek?

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Experimental Results

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Opportunities

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Motivation

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Experiments

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Conclusion & References

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Hardware Details

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Arithmetic Intensity

Modeling Workload Interference

Proble Formulation: Two-Phase Tuning

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Predictor Analysis

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Architecture Overview

A Deep Dive Into Semantic Segmentation Evaluation Metrics

82 Stories To Learn About Neural Networks

QLoRA: Fine-Tuning Your LLMs With a Single GPU