Diagnostic Visualization for Deep Neural Networks Using Stochastic Gradient Langevin Dynamics

Abstract

The internal states of most deep neural networks are difficult to interpret, which makes diagnosis and debugging during training challenging. Activation maximization methods are widely used, but lead to multiple optima and are hard to interpret (appear noise-like) for complex neurons. Image-based methods use maximally-activating image regions which are easier to interpret, but do not provide pixel-level insight into why the neuron responds to them. In this work we introduce an MCMC method: Langevin Dynamics Activation Maximization (LDAM), which is designed for diagnostic visualization. LDAM provides two affordances in combination: the ability to explore the set of maximally activating pre-images, and the ability to trade-off interpretability and pixel-level accuracy using a GAN-style discriminator as a regularizer. We present case studies on MNIST, CIFAR and ImageNet datasets exploring these trade-offs. Finally we show that diagnostic visualization using LDAM leads to a novel insight into the parameter averaging method for deep net training.

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Residual Learning for Image Recognition
• Striving for Simplicity: The All Convolutional Net
• SmoothGrad: removing noise by adding noise
• Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
• Adding Gradient Noise Improves Learning for Very Deep Networks
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
• Women also Snowboard: Overcoming Bias in Captioning Models
• Direct-Manipulation Visualization of Deep Networks
• Noisy Activation Functions
• Activation Maximization Generative Adversarial Nets