Collection:
Deep neural networks (DNNs) are successful in applications with matching inference and training distributions. In real-world scenarios, DNNs have to cope with truly new data samples during inference, potentially coming from a shifted data distribution. Th
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Videos in this product
Acoustic Scene Classification For Mismatched Recording Devices Using Heated-Up Softmax And Spectrum Correction
Deep neural networks (DNNs) are successful in applications with matching inference and training distributions. In real-world scenarios, DNNs have to cope with truly new data samples during inference, potentially coming from a shifted data distribution. Th
Acoustic Scene Classification For Mismatched Recording Devices Using Heated-Up Softmax And Spectrum Correction
Deep neural networks (DNNs) are successful in applications with matching inference and training distributions. In real-world scenarios, DNNs have to cope with truly new data samples during inference, potentially coming from a shifted data distribution. Th