ResNet-18
PulseAugur coverage of ResNet-18 — every cluster mentioning ResNet-18 across labs, papers, and developer communities, ranked by signal.
4 天有情绪数据
-
Research explores how sparsity allocation affects neural network recovery after pruning
A new research paper investigates how the allocation of sparsity in neural networks impacts their ability to recover accuracy after pruning, especially when labeled retraining data is unavailable. The study compares dif…
-
New method efficiently removes client data from federated learning models
Researchers have developed a new method called HF-KCU to efficiently remove a client's data contribution from federated learning models, addressing the computational burden of retraining. This approach approximates the …
-
Intel NCS2 shows significant fault vulnerability under EM injection
Researchers have characterized the fault response of the Intel Neural Compute Stick 2 (NCS2) when subjected to electromagnetic fault injection. Their experiments revealed four distinct outcome classes, including silent …
-
CNNs achieve 96% accuracy classifying partial discharge using novel AWA patterns
Researchers have developed a novel Amplitude-Width-Area (AWA) pattern representation to analyze partial discharge (PD) pulses under switching-voltage excitation. This method maps PD pulses into visual patterns using amp…
-
New compute-in-memory macro boosts edge AI inference efficiency
Researchers have developed E-ReCON, a novel compute-in-memory (CIM) macro designed for efficient AI inference on edge devices. This macro utilizes a compact ReRAM bitcell capable of performing multiplication for both co…
-
New LLM vulnerabilities found in compilation and trigger strength
Researchers have identified new vulnerabilities in large language models (LLMs) related to optimization techniques used during deployment. One study reveals that compilation processes, intended for efficiency, can be ex…
-
CurvSSL framework enhances self-supervised learning with manifold geometry
Researchers have introduced CurvSSL, a novel self-supervised learning framework that incorporates local manifold geometry into its training process. This method augments standard SSL techniques by adding a curvature-bas…
-
AI model grades knee osteoarthritis severity on limited devices
Researchers have developed a novel approach for grading knee osteoarthritis severity using a combination of deep learning and a large language model. The system utilizes a ResNet-18 convolutional neural network, optimiz…
-
GONO optimizer adapts Adam's momentum using directional consistency for better convergence
Researchers have introduced the GONO framework, an optimization signal designed to improve deep learning training by addressing the decoupling of directional alignment and loss convergence. Unlike existing optimizers th…
-
TwistNet-2D learns second-order channel interactions for texture recognition
Researchers have developed TwistNet-2D, a novel module designed to enhance texture recognition by capturing second-order channel interactions. This module computes local pairwise channel products with directional spatia…
-
Unified Map Prior Encoder enhances autonomous driving mapping and planning
Researchers have developed a Unified Map Prior Encoder (UMPE) designed to integrate diverse map data, such as HD/SD vector maps, rasterized maps, and satellite imagery, into autonomous driving systems. This encoder addr…
-
MultiSense-Pneumo framework integrates multimodal data for pneumonia screening
Researchers have developed MultiSense-Pneumo, a multimodal learning framework designed for pneumonia screening in resource-limited areas. This system integrates various data types including symptoms, cough audio, spoken…
-
KAYRA AI system offers flexible cloud/on-premise deployment for karyotyping
Researchers have developed KAYRA, a microservice architecture for AI-assisted karyotyping designed for clinical cytogenetic laboratories. The system integrates multiple machine learning models, including semantic segmen…
-
NeuroPlastic optimizer enhances deep learning with biologically inspired plasticity
Researchers have developed NeuroPlastic, a novel optimization algorithm for deep learning that draws inspiration from biological synaptic plasticity. This method augments standard gradient-based updates with a multi-sig…
-
Researchers analyze Adam's tradeoffs and enhance SignSGD with hybrid switching strategy
Two new research papers explore advancements in optimization algorithms for machine learning. One paper provides a theoretical analysis of the Adam optimizer, detailing its performance under non-stationary objectives an…
-
Canonical knowledge distillation proves effective for semantic segmentation
A new research paper demonstrates that standard knowledge distillation techniques are surprisingly effective for semantic segmentation tasks. The study found that when accounting for computational budget, canonical logi…