Search Results for author:
Found 39 papers, 12 papers with code
Towards End-to-End Structure Solutions from Information-Compromised Diffraction Data via Generative Deep Learning
The revolution in materials in the past century was built on a knowledge of the atomic arrangements and the structure-property relationship.
Accelerating Meta-Learning by Sharing Gradients
The success of gradient-based meta-learning is primarily attributed to its ability to leverage related tasks to learn task-invariant information.
Principled Weight Initialization for Hypernetworks
Hypernetworks are meta neural networks that generate weights for a main neural network in an end-to-end differentiable manner.
Balanced and Deterministic Weight-sharing Helps Network Performance
We also present two novel hash functions, the Dirichlet hash and the Neighborhood hash, and use them to demonstrate experimentally that balanced and deterministic weight-sharing helps with the performance of a neural network.
Assessing SATNet's Ability to Solve the Symbol Grounding Problem
We propose an MNIST based test as an easy instance of the symbol grounding problem that can serve as a sanity check for differentiable symbolic solvers in general.
Teaching Robots to Build Simulations of Themselves
Simulation enables robots to plan and estimate the outcomes of prospective actions without the need to physically execute them.
Knolling Bot: Learning Robotic Object Arrangement from Tidy Demonstrations
Addressing the challenge of organizing scattered items in domestic spaces is complicated by the diversity and subjective nature of tidiness.
High-Degrees-of-Freedom Dynamic Neural Fields for Robot Self-Modeling and Motion Planning
A robot self-model is a task-agnostic representation of the robot's physical morphology that can be used for motion planning tasks in absence of classical geometric kinematic models.
Direct Robot Configuration Space Construction using Convolutional Encoder-Decoders
Real-time motion planning requires accurate and efficient construction of configuration spaces.
On the Origins of Self-Modeling
Self-Modeling is the process by which an agent, such as an animal or machine, learns to create a predictive model of its own dynamics.
Discovering State Variables Hidden in Experimental Data
All physical laws are described as relationships between state variables that give a complete and non-redundant description of the relevant system dynamics.
Visual design intuition: Predicting dynamic properties of beams from raw cross-section images
In this work we aim to mimic the human ability to acquire the intuition to estimate the performance of a design from visual inspection and experience alone.
Full-Body Visual Self-Modeling of Robot Morphologies
Internal computational models of physical bodies are fundamental to the ability of robots and animals alike to plan and control their actions.
Smile Like You Mean It: Driving Animatronic Robotic Face with Learned Models
At present, progress in this field is hindered by the fact that each facial expression needs to be programmed by humans.
The Boombox: Visual Reconstruction from Acoustic Vibrations
Due to the many ways that robots use containers, we believe the box will have a number of applications in robotics.
Visual Perspective Taking for Opponent Behavior Modeling
We suggest that visual behavior modeling and perspective taking skills will play a critical role in the ability of physical robots to fully integrate into real-world multi-agent activities.
Beyond Categorical Label Representations for Image Classification
Our experiments reveal that high dimensional, high entropy labels achieve comparable accuracy to text (categorical) labels on the standard image classification task, but features learned through our label representations exhibit more robustness under various adversarial attacks and better effectiveness with a limited amount of training data.
Visual Hide and Seek
We train embodied agents to play Visual Hide and Seek where a prey must navigate in a simulated environment in order to avoid capture from a predator.
Zero Shot Learning on Simulated Robots
Task transfer is achieved using a self-model that encapsulates the dynamics of a system and serves as an environment for reinforcement learning.
Automated Weed Detection in Aerial Imagery with Context
In this paper, we demonstrate the ability to discriminate between cultivated maize plant and grass or grass-like weed image segments using the context surrounding the image segments.
Ensemble Model Patching: A Parameter-Efficient Variational Bayesian Neural Network
Two main obstacles preventing the widespread adoption of variational Bayesian neural networks are the high parameter overhead that makes them infeasible on large networks, and the difficulty of implementation, which can be thought of as "programming overhead."
Predicting the accuracy of neural networks from final and intermediate layer outputs
We show that information about whether a neural network's output will be correct or incorrect is present in the outputs of the network's intermediate layers.
Seven Myths in Machine Learning Research
We present seven myths commonly believed to be true in machine learning research, circa Feb 2019.
Agent Embeddings: A Latent Representation for Pole-Balancing Networks
Linearly interpolating between the latent embeddings for a good agent and a bad agent yields an agent embedding that generates a network with intermediate performance, where the performance can be tuned according to the coefficient of interpolation.
Neural Network Quine
We also describe a method we call regeneration to train the network without explicit optimization, by injecting the network with predictions of its own parameters.
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them.
Autostacker: A Compositional Evolutionary Learning System
We introduce an automatic machine learning (AutoML) modeling architecture called Autostacker, which combines an innovative hierarchical stacking architecture and an Evolutionary Algorithm (EA) to perform efficient parameter search.
Autostacker: an Automatic Evolutionary Hierarchical Machine Learning System
We significantly reduce the time of AutoML with a naturally inspired algorithm - Parallel Hill Climbing (PHC).
Scalable Co-Optimization of Morphology and Control in Embodied Machines
In psychology, the theory of embodied cognition posits that behavior arises from a close coupling between body plan and sensorimotor control, which suggests why co-optimizing these two subsystems is so difficult: most evolutionary changes to morphology tend to adversely impact sensorimotor control, leading to an overall decrease in behavioral performance.
Convergent Learning: Do different neural networks learn the same representations?
Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers.
Understanding Neural Networks Through Deep Visualization
The first is a tool that visualizes the activations produced on each layer of a trained convnet as it processes an image or video (e. g. a live webcam stream).
How transferable are features in deep neural networks?
Such first-layer features appear not to be specific to a particular dataset or task, but general in that they are applicable to many datasets and tasks.
Computing Entropy Rate Of Symbol Sources & A Distribution-free Limit Theorem
Entropy rate of sequential data-streams naturally quantifies the complexity of the generative process.
Data Smashing
Here, we propose a universal solution to this problem: we delineate a principle for quantifying similarity between sources of arbitrary data streams, without a priori knowledge, features or training.
Hands-free Evolution of 3D-printable Objects via Eye Tracking
Interactive evolution has shown the potential to create amazing and complex forms in both 2-D and 3-D settings.
The evolutionary origins of modularity
A central biological question is how natural organisms are so evolvable (capable of quickly adapting to new environments).
