Search Results for author:
Found 11 papers, 1 papers with code
Scaling Instructable Agents Across Many Simulated Worlds
Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI.
Explainability Via Causal Self-Talk
We take a pragmatic view of the issue, and define a set of desiderata that capture both the ambitions of XAI and the practical constraints of deep learning.
Transformers generalize differently from information stored in context vs in weights
In transformers trained on controlled stimuli, we find that generalization from weights is more rule-based whereas generalization from context is largely exemplar-based.
Tracking Without Re-recognition in Humans and Machines
For this, we introduce PathTracker, a synthetic visual challenge that asks human observers and machines to track a target object in the midst of identical-looking "distractor" objects.
Recurrent neural circuits for contour detection
We introduce a deep recurrent neural network architecture that approximates visual cortical circuits.
Disentangling neural mechanisms for perceptual grouping
Forming perceptual groups and individuating objects in visual scenes is an essential step towards visual intelligence.
Learning long-range spatial dependencies with horizontal gated recurrent units
Progress in deep learning has spawned great successes in many engineering applications.
Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks
We first demonstrate that current state-of-the-art approaches to neuron segmentation perform poorly on the challenge.
Learning long-range spatial dependencies with horizontal gated-recurrent units
As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching -- and sometimes even surpassing -- human accuracy on a variety of visual recognition tasks.
Same-different problems strain convolutional neural networks
The robust and efficient recognition of visual relations in images is a hallmark of biological vision.
Not-So-CLEVR: Visual Relations Strain Feedforward Neural Networks
The robust and efficient recognition of visual relations in images is a hallmark of biological vision.
