Search Results for author:
Found 11 papers, 6 papers with code
Multimodal Neurons in Artificial Neural Networks
It’s the fact that you plug visual information into the rich tapestry of memory that brings it to life."
Visualizing Weights
Trying to understand artificial neural networks also has a lot in common with neuroscience, which tries to understand biological neural networks.
High-Low Frequency Detectors
Yet, when systematically characterizing the early layers of InceptionV1, we found a full fifteen neurons of mixed3a that appear to detect a high frequency pattern on one side, and a low frequency pattern on the other.
Thread: Circuits
To facilitate exploration of this direction, Distill is inviting a “thread” of short articles on circuits, interspersed with critical commentary by experts in adjacent fields.
Feature Visualization
There is a growing sense that neural networks need to be interpretable to humans.
Activation Atlas
By using feature inversion to visualize millions of activations from an image classification network, we create an explorable activation atlas of features the network has learned which can reveal how the network typically represents some concepts.
An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents
We lessen this friction, by (1) training several algorithms at scale and releasing trained models, (2) integrating with a previous Deep RL model release, and (3) releasing code that makes it easy for anyone to load, visualize, and analyze such models.
Differentiable Image Parameterizations
Typically, we parameterize the input image as the RGB values of each pixel, but that isn’t the only way.
The Building Blocks of Interpretability
In this article, we treat existing interpretability methods as fundamental and composable building blocks for rich user interfaces.
