Optimizes energy efficiency in wireless sensor networks with limited information.
problem Maximizing energy efficiency in energy harvesting wireless sensor networks with limited channel state information.
method Modeling as a Multi-Armed Bandits problem and developing an Upper Confidence Bound algorithm.
result Significant gains in energy efficiency compared to benchmark schemes.
Energy-efficient sampling for machine learning using magnetic tunnel junctions.
problem Costly and inefficient random sampling in machine learning.
method Energy-efficient algorithm using stochastic magnetic tunnel junctions for uniform Float16 sampling.
result Higher energy efficiency than state-of-the-art algorithms, with a minimum factor of 9721.
QubitHD improves HD computing ML efficiency without sacrificing accuracy.
problem Trade-off between energy efficiency and classification accuracy in HD computing-based ML.
method Stochastically binarizes HD-based algorithms while maintaining comparable classification accuracies.
result 65% improvement in energy efficiency and 95% improvement in training time on FPGA.
MER-SDN uses machine learning to optimize energy efficiency in SDN networks.
problem Energy efficiency in SDN networks is challenging and impacts both economics and environment.
method Feature extraction, training, and testing phases of a machine learning framework.
result Achieves up to 25X speedup in predicting optimal parameters for energy efficient routing.
Energy-efficient detection of natural errors in deep networks.
problem Deep networks lack error detection capability without additional energy costs.
method Append RACs at hidden layers to detect natural errors with early classification termination.
result Early classification termination reduces energy consumption.
E2GC optimizes energy efficiency in DNNs by balancing computational and data movement costs.
problem Imbalance between computational complexity and data reuse in GConv leads to suboptimal energy efficiency.
method Developed an optimum group size model and proposed E2GC module with constant group size.
result E2GC modules improve energy efficiency by 10.8% and 4.73% on P100 and P4000 GPUs, respectively.
Improves energy efficiency of neuromorphic hardware by optimizing memory organization and encoding schemes.
problem Energy inefficiency in neuromorphic hardware, especially in digital accelerators.
method Synthesized controller and memory for different encoding schemes, introduced functional encoding for structured connectivity.
result Functional encoding offers a 58% reduction in energy for weight updates in convolutional layers.
Paper optimizes UAV navigation for IoT data freshness and energy efficiency.
problem Improving data freshness and connectivity for IoT devices with UAVs.
method Deep reinforcement learning model with experience replay for energy-efficient UAV trajectory optimization.
result The proposed approach is 3.6% and 3.13% more energy efficient than greedy and baseline methods.
Novel framework finds globally optimal energy-efficient power control in wireless networks.
problem Energy-efficient power control in wireless networks.
method Branch-and-bound procedure with problem-specific bounds for faster convergence.
result Global solution for common energy-efficient power control problems with reduced complexity.
Bayesian model for energy-efficient EV navigation.
problem Limited battery capacity in electric vehicles.
method Bayesian modeling and online learning framework with exploration strategies.
result Established rigorous regret bounds for Thompson Sampling.
Improved neural architecture optimization for energy efficiency.
problem Designing energy-efficient deep learning networks for mobile and edge devices.
method Incorporates energy cost in splitting process and uses a scalable stochastic gradient algorithm to speed up the splitting.
result Trains highly accurate and energy-efficient networks on challenging datasets like ImageNet.
A new SNN learning algorithm for energy-efficient VLSI circuits.
problem Designing energy-efficient SNNs for VLSI implementation.
method Temporal coding, analog VLSI, resistive memory.
result Classification accuracy comparable to state-of-the-art temporal coding SNN algorithms.
Compact DNNs increase memory footprint and reduce energy efficiency.
problem Designing compact deep neural networks (DNNs) for improved energy efficiency.
method Evaluation of recently proposed compact DNNs on a Tesla P100 GPU.
result Higher number of activations and memory footprint lead to reduced energy efficiency.
DRL-DPT improves energy efficiency in wireless networks with deterministic power control.
problem Severe performance degradation in traditional ICIC schemes with complex interference patterns.
method Deep Reinforcement Learning with Deterministic Policy and Target (DRL-DPT) framework.
result Consistently outperforms existing schemes in terms of energy efficiency and throughput.
The paper tackles decision-oriented communications for energy-efficient resource allocation.
problem Maximizing utility functions under quantized information.
method Develops solutions for quantizing information to maximize utility functions under known and observed conditions.
result Quantizing the state roughly is optimal for sum-rate maximization but not for energy-efficiency metrics.
Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations. The recent pruning based work ESE suffers from degradation of performance/energy efficiency due to the irregular network structure after pruning. We propose bl…
Quantum computing offers energy savings over classical computing.
problem Energy efficiency in computing services.
method Cournot competition model constrained by energy usage.
result Quantum computing firms can outperform classical counterparts in energy efficiency.
Optimal design portfolios improve energy efficiency and reduce risk in uncertain reservoirs.
problem Uncertain reservoir conditions lead to unstable gas recovery and low resource efficiency.
method Developed optimal portfolios of well designs based on reservoir conditions and probabilities.
result Remarkable reduction in variation and substantial increase in energy efficiency achieved.
SmartDeal reduces energy and storage costs for deep neural networks.
problem Heavy parameterization of deep neural networks leads to inefficient use of DRAM.
method SmartDeal decomposes weights into a small basis matrix and a structurally sparse coefficient matrix, quantized to power-of-2.
result Up to 2.44x energy efficiency improvement in inference and 10.56x reduction in training energy.
Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy. For DNNs, the model size is an important factor affecting performance, scalability and energy efficiency. Weig…
Enhanced tabular benchmarks for energy-efficient neural architecture search.
problem Energy consumption in deep learning models.
method Introducing EC-NAS, an enhanced tabular benchmark with energy consumption data.
result EC-NAS reveals a balance between energy usage and accuracy in neural architecture search.
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia. The aim of this paper is to achieve ultra-high energy efficiency and performance for hardware implementations of deep neural networks (DNNs). An algorithm-hardware co-optimization framework is developed, which i…
Improved SNNs with quantized activations outperform traditional networks.
problem Maintaining SotA accuracy in SNNs with limited bit precision.
method Interpolating between non-spiking and spiking regimes using signal processing tools.
result First hybrid SNN outperforms traditional RNNs in accuracy with reduced bit precision.
Efficient hybrid networks improve AI performance at the edge.
problem Achieving AI performance at the edge with minimal energy and memory usage.
method Proposed hybrid networks combining binary and full-precision layers.
result Hybrid networks achieve close to full-precision performance with up to 21.8x memory compression.
New pruning methods improve energy efficiency of neural networks.
problem Energy-efficient neural networks for devices with limited resources.
method Magnitude and Gradient based pruning at initialization and training of sparse architectures.
result Proposed novel pruning methods prevent full layer pruning and improve training.
Proposes a game-theoretic framework to motivate energy-efficient behavior in smart buildings.
problem Improving energy efficiency in smart building infrastructure through occupant behavior.
method Introduces a novel game-theoretic framework with human interaction, incorporating utility learning and deep neural networks.
result Demonstrates highly accurate prediction of occupant energy resource usage and explainable decision-making.
A new energy-efficient pruning method for federated learning.
problem Energy inefficiency in gradient sparsification for federated learning.
method Formalized energy-constrained projection problem and proposed Cost-Weighted Magnitude Pruning (CWMP).
result CWMP optimally balances performance and energy efficiency in federated learning.
Stella Nera accelerates matrix multiplications with a hash-based approach, achieving high energy efficiency and accuracy.
problem High computational and energy demands due to matrix multiplications in AI models.
method Stella Nera uses Maddness, a hash-based product quantization, to eliminate multipliers and achieve lookups and additions.
result Achieved an energy efficiency of 161 TOp/s/W@0.55V, 25x better than conventional MatMul accelerators.
FixyNN improves energy efficiency of mobile computer vision tasks.
problem High energy consumption of state-of-the-art CNN models on mobile devices.
method Fixed-weight feature extractor and programmable CNN accelerator for transfer learning.
result Achieved up to 26.6 TOPS/W energy efficiency, nearly 2x more efficient than conventional accelerators.
EDCompress optimizes energy efficiency of CNN models on edge devices.
problem Low energy consumption for edge devices with diverse dataflow types.
method Energy-aware model compression using reinforcement learning.
result Improves energy efficiency by 20X, 17X, 37X in various networks.
Paper tackles energy efficiency in FL over wireless networks.
problem Energy efficient transmission and computation resource allocation for FL over wireless networks.
method Formulated as an optimization problem, iterative algorithm derived with closed-form solutions for time, bandwidth, power, and accuracy.
result Proposed algorithms reduce up to 59.5% energy consumption compared to conventional FL methods.
SEFR is a fast, energy-efficient classifier for ultra-low power devices.
problem Running machine learning on battery-powered devices is challenging due to time and energy constraints.
method SEFR is an ultra-low power classifier with linear time complexity for training and testing.
result SEFR is 63 times faster and 70 times more energy efficient than state-of-the-art classifiers.
SmartExchange trades memory for computation in neural networks.
problem Energy-efficient inference of deep neural networks.
method Algorithm-hardware co-design framework integrating sparsification, decomposition, and quantization.
result SmartExchange reduces energy consumption and improves performance.
Optimizes deep reinforcement learning for energy-efficient video streaming.
problem Minimizing energy consumption in video streaming over mobile networks.
method Integrates DDPG algorithm with partially known model to reduce signaling overhead and improve convergence speed.
result Proposed policy converges to optimal policy with improved convergence speed.
FPDeep accelerates CNN training on FPGA clusters with high parallelism and energy efficiency.
problem Scaling DNN training to large clusters with high utilization and balanced workload.
method Hybrid model and layer parallelism, fine-grained pipeline, balanced workload partitioning.
result FPDeep achieves high parallelism and utilization, reducing storage demand to on-chip memory.
New loss improves OOD detection without extra data or tuning.
problem Improving OOD detection without additional data or tuning.
method Proposed IsoMax loss and entropic score to replace SoftMax loss.
result Training with IsoMax loss significantly improves OOD detection performance.
Paper presents an energy-efficient RL method for sensor networks.
problem Energy consumption in sensor networks for health monitoring.
method Adaptive Reinforcement Learning framework using SARSA algorithm.
result Achieves performance enhancement and energy savings over time.
Paper tackles intermittent learning for energy-constrained machine learning tasks.
problem Energy-constrained machine learning tasks on intermittently powered systems.
method Developed an algorithm and heuristics for efficient learning under energy constraints.
result Improves energy efficiency by up to 100% and reduces learning examples by up to 50%.
SNNs as first-to-spike policies improve energy efficiency in RL control.
problem Reducing energy consumption in RL control systems.
method Policy gradient approach with GLM for spiking neurons.
result Online trained SNNs outperform ANN conversion in energy efficiency and control performance.
Paper proposes MCMA architecture for neural approximate computing with higher invocation rate and energy savings.
problem Limited invocation rate of neural approximators leading to suboptimal energy efficiency.
method Introduces MCMA architecture with a multiclass classifier and multiple approximators, sharing hardware resources and efficiently swapping approximators.
result Significantly higher invocation rate and energy savings compared to existing methods.
FixyNN splits CNN models into fixed and trainable parts for efficient on-device inference.
problem Energy inefficiency in on-device CNN inference for real-time computer vision.
method Co-designed hardware accelerator platform with transfer learning for training.
result Achieved nearly 2x better energy efficiency than a conventional accelerator.
FANN-on-MCU enables efficient neural network inference on IoT devices.
problem Energy-efficient neural network inference on resource-constrained IoT devices.
method Open-source toolkit for ARM Cortex-M and RISC-V microcontrollers.
result Efficient neural network execution with low latency and power consumption.
A hybrid neural network optimizes AI deployment on edge and cloud for energy efficiency.
problem Energy and resource constraints in edge devices for deep learning models.
method Conditionally deep hybrid neural network with quantized layers at edge and full-precision layers at cloud.
result Early classification at the edge reduces energy consumption by 5.5x on CIFAR-10 dataset.
Memory-augmented neural networks (MANNs) are designed for question-answering tasks. It is difficult to run a MANN effectively on accelerators designed for other neural networks (NNs), in particular on mobile devices, because MANNs require recurrent data paths and various types of operations related to external memory a…
Machine Learning (ML) algorithms, like Convolutional Neural Networks (CNN), Support Vector Machines (SVM), etc. have become widespread and can achieve high statistical performance. However their accuracy decreases significantly in energy-constrained mobile and embedded systems space, where all computations need to be c…
New HANNA architecture improves accuracy, latency, and energy efficiency for mobile devices.
problem Designing neural networks optimized for specific hardware devices.
method Differentiable NAS method with energy term added to loss function.
result HANNA achieves significant speedup and energy efficiency over MobileNetv2 and CondenseNet.
HRL4IN tackles interactive navigation tasks with mobile manipulators, improving efficiency and performance.
problem Interactive Navigation tasks require mobile manipulators to perform various actions, but choosing the right part of the embodiment is inefficient.
method HRL4IN uses a hierarchical reinforcement learning architecture to handle heterogeneous phases of navigation and manipulation, selecting the appropriate part of the embodiment for each phase.
result HRL4IN significantly outperforms flat PPO and HAC in terms of task performance and energy efficiency.
This paper tackles energy-efficient machine learning on low-power devices.
problem Energy consumption in machine learning due to data communication.
method Dynamic averaging for integer exponential families on low-power processors.
result Achieves comparable model quality with significantly less communication and energy.