GoogLeNet
PulseAugur coverage of GoogLeNet — every cluster mentioning GoogLeNet across labs, papers, and developer communities, ranked by signal.
-
InferNet exploits GPU profiles for DNN architecture inference
Researchers have developed InferNet, a novel method for inferring the architecture of deep neural networks (DNNs) by analyzing aggregate GPU profiles. This technique bypasses the need for complex, fine-grained data anal…
-
New method optimizes DNNs for edge devices, cutting latency with minimal accuracy loss
Researchers have developed a new method for optimizing deep neural network architectures for edge devices, focusing on meeting strict latency constraints while maintaining high accuracy. This approach utilizes a latency…
-
Block-sparse featurizers capture visual concept manifolds
Researchers have developed block-sparse featurizers (BSFs) that can more effectively capture the geometric structure of visual concepts within neural network activations. These BSFs group directions into blocks, alignin…
-
New research explains why deep neural networks learn features consistently
Researchers have established feature-learning consistency guarantees for a specific class of deep neural networks (DNNs) known as sublinearly structured DNNs. These networks, characterized by input/output dimensions and…
-
Network pruning impacts GoogLeNet performance and interpretability
Researchers investigated how network pruning affects the performance and interpretability of GoogLeNet on ImageNet. They applied various pruning techniques and retraining strategies, finding that performance could be ma…