• Corpus ID: 221093845

Fine-Tuning Using Grid Search & Gradient Visualization Technical Report

@inproceedings{Hou2020FineTuningUG,
  title={Fine-Tuning Using Grid Search \& Gradient Visualization Technical Report},
  author={Bowei Hou and Kacper Radzikowski and Ahmed Mohammed Farid},
  year={2020}
}
In this technical report, we briefly describe the models used in the task 4 challenge of DCASE2020. We utilized previously available models and fine-tuned them using the grid search algorithm and gradient visualization. This is the first attempt by our team to enter a competition on sound source manipulation. 

Tables from this paper

References

SHOWING 1-6 OF 6 REFERENCES
MEAN TEACHER WITH DATA AUGMENTATION FOR DCASE 2019 TASK 4 Technical Report
TLDR
A mean-teacher model with convolutional neural network (CNN) and recurrent neuralnetwork (RNN) together with data augmentation and a median window tuned for each class based on prior knowledge is proposed.
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
TLDR
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks, but it becomes unwieldy when learning large datasets, so Mean Teacher, a method that averages model weights instead of label predictions, is proposed.
Freesound Datasets: A Platform for the Creation of Open Audio Datasets
Comunicacio presentada al 18th International Society for Music Information Retrieval Conference celebrada a Suzhou, Xina, del 23 al 27 d'cotubre de 2017.
Universal Sound Separation
TLDR
A dataset of mixtures containing arbitrary sounds is developed, and the best methods produce an improvement in scale-invariant signal-to-distortion ratio of over 13 dB for speech/non-speech separation and close to 10 dB for universal sound separation.
What's all the fuss about?
TLDR
As a patient representative on the Care Record Development Board, it seems to me that the finer points of the opt-in or opt-out argument may be lost on even the most well informed patients.
Exploring Gradients
  • Weights & Biases,
  • 2019