A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommendations
Modern deep neural networks, particularly recent large language models, come with
massive model sizes that require significant computational and storage resources. To …
massive model sizes that require significant computational and storage resources. To …
Making models shallow again: Jointly learning to reduce non-linearity and depth for latency-efficient private inference
Large number of ReLU and MAC operations of Deep neural networks make them ill-suited
for latency and compute-efficient private inference. In this paper, we present a model …
for latency and compute-efficient private inference. In this paper, we present a model …
CoPriv: network/protocol co-optimization for communication-efficient private inference
Deep neural network (DNN) inference based on secure 2-party computation (2PC) can offer
cryptographically-secure privacy protection but suffers from orders of magnitude latency …
cryptographically-secure privacy protection but suffers from orders of magnitude latency …
Updp: A unified progressive depth pruner for cnn and vision transformer
Traditional channel-wise pruning methods by reducing network channels struggle to
effectively prune efficient CNN models with depth-wise convolutional layers and certain …
effectively prune efficient CNN models with depth-wise convolutional layers and certain …
Deep learning-assisted unmanned aerial vehicle flight data anomaly detection: A review
L Yang, S Li, Y Zhang, C Zhu, Z Liao - IEEE Sensors Journal, 2024 - ieeexplore.ieee.org
Flight data anomaly detection is crucial for ensuring the flight safety of unmanned aerial
vehicles (UAVs). By monitoring and analyzing flight data, anomalies can be detected in time …
vehicles (UAVs). By monitoring and analyzing flight data, anomalies can be detected in time …
Tinyml design contest for life-threatening ventricular arrhythmia detection
The first ACM/IEEE TinyML Design Contest (TDC) held at the 41st International Conference
on Computer-Aided Design (ICCAD) in 2022 is a challenging, multimonth, research and …
on Computer-Aided Design (ICCAD) in 2022 is a challenging, multimonth, research and …
[HTML][HTML] Benchmarking In-Sensor Machine Learning Computing: An Extension to the MLCommons-Tiny Suite
This paper proposes a new benchmark specifically designed for in-sensor digital machine
learning computing to meet an ultra-low embedded memory requirement. With the …
learning computing to meet an ultra-low embedded memory requirement. With the …
Model Lightweighting for Real‐time Distraction Detection on Resource‐Limited Devices
J Wang, ZC Wu - Computational Intelligence and Neuroscience, 2022 - Wiley Online Library
Detecting distracted driving accurately and quickly with limited resources is an essential yet
underexplored problem. Most of the existing works ignore the resource‐limited reality. In this …
underexplored problem. Most of the existing works ignore the resource‐limited reality. In this …
Efficient latency-aware cnn depth compression via two-stage dynamic programming
Recent works on neural network pruning advocate that reducing the depth of the network is
more effective in reducing run-time memory usage and accelerating inference latency than …
more effective in reducing run-time memory usage and accelerating inference latency than …
Restructurable activation networks
K Bhardwaj, J Ward, C Tung, D Gope, L Meng… - arXiv preprint arXiv …, 2022 - arxiv.org
Is it possible to restructure the non-linear activation functions in a deep network to create
hardware-efficient models? To address this question, we propose a new paradigm called …
hardware-efficient models? To address this question, we propose a new paradigm called …