Fast Monte Carlo Dropout and Error Correction for Radio Transmitter Classification
This work addresses computational bottlenecks in uncertainty estimation for domain-specific applications like RF transmitter classification, offering an incremental improvement over existing methods.
The paper tackles the computational inefficiency of Monte Carlo dropout for uncertainty estimation in deep learning by enabling dropout only near the output and reusing prior computations, combined with error correction using side information. Applied to RF transmitter classification, it shows improved prediction uncertainty and effective identification of unseen transmitters while maintaining accuracy on trained ones.
Monte Carlo dropout may effectively capture model uncertainty in deep learning, where a measure of uncertainty is obtained by using multiple instances of dropout at test time. However, Monte Carlo dropout is applied across the whole network and thus significantly increases the computational complexity, proportional to the number of instances. To reduce the computational complexity, at test time we enable dropout layers only near the output of the neural network and reuse the computation from prior layers while keeping, if any, other dropout layers disabled. Additionally, we leverage the side information about the ideal distributions for various input samples to do `error correction' on the predictions. We apply these techniques to the radio frequency (RF) transmitter classification problem and show that the proposed algorithm is able to provide better prediction uncertainty than the simple ensemble average algorithm and can be used to effectively identify transmitters that are not in the training data set while correctly classifying transmitters it has been trained on.