Search Results for author:
Found 10 papers, 6 papers with code
CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images
This task presents two challenges: (1) high-resolution CC images lack the captions necessary to train text-to-image generative models; (2) CC images are relatively scarce.
CA$^2$T-Net: Category-Agnostic 3D Articulation Transfer from Single Image
We present a neural network approach to transfer the motion from a single image of an articulated object to a rest-state (i. e., unarticulated) 3D model.
Towards Understanding How Machines Can Learn Causal Overhypotheses
Recent work in machine learning and cognitive science has suggested that understanding causal information is essential to the development of intelligence.
Learning Causal Overhypotheses through Exploration in Children and Computational Models
Despite recent progress in reinforcement learning (RL), RL algorithms for exploration still remain an active area of research.
GANmouflage: 3D Object Nondetection with Texture Fields
Our model learns to camouflage a variety of object shapes from randomly sampled locations and viewpoints within the input scene, and is the first to address the problem of hiding complex object shapes.
ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
ABO contains product catalog images, metadata, and artist-created 3D models with complex geometries and physically-based materials that correspond to real, household objects.
Exploring Exploration: Comparing Children with RL Agents in Unified Environments
Research in developmental psychology consistently shows that children explore the world thoroughly and efficiently and that this exploration allows them to learn.
Accelerating Training of Deep Neural Networks with a Standardization Loss
We find that a standardization loss accelerates training on both small- and large-scale image classification experiments, works with a variety of architectures, and is largely robust to training across different batch sizes.
Capacity and Trainability in Recurrent Neural Networks
They can store an amount of task information which is linear in the number of parameters, and is approximately 5 bits per parameter.
Protein Secondary Structure Prediction Using Deep Multi-scale Convolutional Neural Networks and Next-Step Conditioning
We first train a series of deep neural networks to predict eight-class secondary structure labels given a protein's amino acid sequence information and find that using recent methods for regularization, such as dropout and weight-norm constraining, leads to measurable gains in accuracy.
Protein Secondary Structure Prediction
Protein Structure Prediction
