On-Device Machine Learning: An Algorithms and Learning Theory Perspective
Explore this paper's citation graph
Summary
This survey reformulates the problem of on-device learning as resource constrained learning where the resources are compute and memory to allow tools, techniques, and algorithms from a wide variety of research areas to be compared equitably.
- Type
- preprint
- Published
- 2019-11-02
- Cited by
- 189
- References
- 221
- Access
- Open access
- OpenAlex
- https://openalex.org/W2983872911
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:207780008
Keywords
Computer science, Machine learning, Artificial intelligence, Field (mathematics), Perspective (graphical)
References
- Local Deep Kernel Learning for Efficient Non-linear SVM Prediction
- Fast ConvNets Using Group-Wise Brain Damage
- Computational complexity of machine learning
- Estimation of Dependences Based on Empirical Data
- A new method in neural network supervised training with imprecision
- Linear Regression with Limited Observation
- On-chip backpropagation training using parallel stochastic bit streams
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Streaming Sparse Principal Component Analysis
- Compressing Deep Convolutional Networks using Vector Quantization
- Distilling the Knowledge in a Neural Network
- Minimax rates for memory-bounded sparse linear regression
- Finite precision error analysis for neural network learning
- BinaryConnect: Training Deep Neural Networks with binary weights during propagations
- Improving neural networks by preventing co-adaptation of feature detectors
- Semi-Supervised Learning
- On Learning With Finite Memory
- Compound Hypothesis Testing with Finite Memory
- From average case complexity to improper learning complexity
- Statistical algorithms and a lower bound for detecting planted cliques
Cited by
- DeepShift: Towards Multiplication-Less Neural Networks
- Wireless AI: Enabling an AI-Governed Data Life Cycle
- COVID-MobileXpert: On-Device COVID-19 Screening using Snapshots of Chest X-Ray
- SEFR: A Fast Linear-Time Classifier for Ultra-Low Power Devices
- Exploring the computational cost of machine learning at the edge for human-centric Internet of Things
- Latest Research Trends in Gait Analysis Using Wearable Sensors and Machine Learning: A Systematic Review
- MDLdroidLite: A Release-and-Inhibit Control Approach to Resource-Efficient Deep Neural Networks on Mobile Devices
- DIESEL: A novel deep learning-based tool for SpMV computations and solving sparse linear equation systems
- Bringing AI To Edge: From Deep Learning's Perspective
- Custom Face Classification Model for Classroom Using Haar-Like and LBP Features with Their Performance Comparisons
- Early DGA-based botnet identification: pushing detection to the edges
- Artificial Intelligence for UAV-Enabled Wireless Networks: A Survey
- Machine Learning at Resource Constraint Edge Device Using Bonsai Algorithm
- Resource-aware On-device Deep Learning for Supermarket Hazard Detection
- Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective
- On-Device Learning Systems for Edge Intelligence: A Software and Hardware Synergy Perspective
- On-Device Deep Learning Inference for System-on-Chip (SoC) Architectures
- Federated Learning for Internet of Things: A Comprehensive Survey
- Unlinkable Collaborative Learning Transactions: Privacy-Awareness in Decentralized Approaches
- A Survey on Federated Learning for Resource-Constrained IoT Devices
Related papers
- New theoretical frameworks for machine learning
- Multiple-view multiple-learner active learning
- Survey of Machine Learning Algorithms & its Applications
- Theoretical foundations of active learning
- Theory of Disagreement-Based Active Learning
- Human Active Learning
- Active learning with support vector machines
- A new semi-supervised support vector machine learning algorithm based on active learning