Browsing by Author "Bonet Solé, David"

Now showing items 1-4 of 4

    • Channel redundancy and overlap in convolutional neural networks with channel-wise NNK graphs 

      Bonet Solé, David; Ortega, Antonio; Ruiz Hidalgo, Javier; Shekkizhar, Sarath (Institute of Electrical and Electronics Engineers (IEEE), 2022)
      Conference report
      Open Access
      Feature spaces in the deep layers of convolutional neural networks (CNNs) are often very high-dimensional and difficult to inter-pret. However, convolutional layers consist of multiple channels that are activated by different ...

    • Channel-wise early stopping without a validation set via NNK polytope interpolation 

      Bonet Solé, David; Ortega, Antonio; Ruiz Hidalgo, Javier; Sarath Shekkizhar, Sarath (2021)
      Conference report
      Open Access
      State-of-the-art neural network architectures continue to scale in size and deliver impressive generalization results, although this comes at the expense of limited interpretability. In particular, a key challenge is to ...

    • Improved neural network generalization using channel-wise NNK graph constructions 

      Bonet Solé, David (Universitat Politècnica de Catalunya, 2021-06)
      Bachelor thesis
      Open Access
      Covenantee:   USC Viterbi School of Engineering
      State-of-the-art neural network architectures continue to scale in size and deliver impressive results on unseen data points at the expense of poor interpretability. In the deep layers of these models we often encounter ...

    • Meta-learning for neural network weight prediction and compressive learning 

      Bonet Solé, David (Universitat Politècnica de Catalunya, 2023-09-13)
      Master thesis
      Restricted access - confidentiality agreement
      Covenantee:   Stanford University
      The rapid expansion in the size of new datasets and available data online has led to significant scaling of the size of neural models. However, training deep learning models and performing hyperparameter tuning is ...