Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 5 of 5 for “"activation maximization"”.

  1. Manipulating Explanations: Modifying Feature Visualizatio in in Artificial Neural Networks

    … units of trained deep neural networks. Based on activation maximization, it consists of finding synthetic or natural inputs that maximize neuron activations. This work introduces an optimization framework that aims to deceive feature visualization through adversarial model manipulation. It …

    concordia Download PDF for Manipulating Explanations: Modifying Feature Visualizatio in in Artificial Neural Networks (opens in a new tab)

  2. Deep Neural Network-Based Simulations for Predicting, Controlling, and Characterizing BOLD fMRI Responses

    … how a DNN-based visualization technique called activation maximization can be applied to these simulation models to produce images optimized for specific cortical regions. Analysis of real BOLD responses to these images shows robust modulation of BOLD responses in targeted regions, both within …

    unr Repository record for Deep Neural Network-Based Simulations for Predicting, Controlling, and Characterizing BOLD fMRI Responses (opens in a new tab)

  3. Self-supervised learning using motion and visualizing convolutional neural networks

    … to reconstruct an image from its representation, activation maximization, in which we search for patterns that maximally stimulate a representation component, and caricaturization, in which the visual patterns that a representation detects in an image are exaggerated. We formulate these into a …

    oxford Repository record for Self-supervised learning using motion and visualizing convolutional neural networks (opens in a new tab)

  4. Predicting, Engineering and Interpreting Gene Regulatory Sequences and Proteins with Deep Learning

    … predictor. These methods, which are based on activation maximization, can be used to efficiently generate millions of diverse, optimized sequence designs on the basis of a deep generative model. Finally, we present a feature attribution method for interpreting neural network predictions. The …

    washington Repository record for Predicting, Engineering and Interpreting Gene Regulatory Sequences and Proteins with Deep Learning (opens in a new tab)

  5. Looking under the hood: visualizing what LSTMs learn

    Recurrent Neural Networks (RNNs) such as Long Short Term Memory (LSTM) and Gated Recurrent Units (GRUs) have been successful in many applications involving sequential data. The success of these models lies in the complex feature representations they learn from the training data. One criteria to …

    colostate Repository record for Looking under the hood: visualizing what LSTMs learn (opens in a new tab)