Search Results for author:
Found 23 papers, 4 papers with code
Modular Neural Network Policies for Learning In-Flight Object Catching with a Robot Hand-Arm System
We present a modular framework designed to enable a robot hand-arm system to learn how to catch flying objects, a task that requires fast, reactive, and accurately-timed robot motions.
RObotic MAnipulation Network (ROMAN) $\unicode{x2013}$ Hybrid Hierarchical Learning for Solving Complex Sequential Tasks
In this work, we present a Hybrid Hierarchical Learning framework, the Robotic Manipulation Network (ROMAN), to address the challenge of solving multiple complex tasks over long time horizons in robotic manipulation.
Multi-Epoch Learning for Deep Click-Through Rate Prediction Models
However, it is still unknown whether a multi-epoch training paradigm could achieve better results, as the best performance is usually achieved by one-epoch training.
Deep Stable Multi-Interest Learning for Out-of-distribution Sequential Recommendation
However, none of existing multi-interest recommendation models consider the Out-Of-Distribution (OOD) generalization problem, in which interest distribution may change.
Deep Stable Representation Learning on Electronic Health Records
The unstable correlation between procedures and diagnoses existed in the training distribution can cause spurious correlation between historical EHR and future diagnosis.
Improving Multi-Interest Network with Stable Learning
Modeling users' dynamic preferences from historical behaviors lies at the core of modern recommender systems.
LPFS: Learnable Polarizing Feature Selection for Click-Through Rate Prediction
When training is finished, some gates are exact zero, while others are around one, which is particularly favored by the practical hot-start training in the industry, due to no damage to the model performance before and after removing the features corresponding to exact-zero gates.
Slimmable Video Codec
Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands.
Deep Active Learning for Text Classification with Diverse Interpretations
To train high-performing models with the minimal annotation cost, active learning is proposed to select and label the most informative samples, yet it is still challenging to measure informativeness of samples used in DNNs.
DNN2LR: Automatic Feature Crossing for Credit Scoring
Accordingly, we can design an automatic feature crossing method to find feature interactions in DNN, and use them as cross features in LR.
STAN: Spatio-Temporal Attention Network for Next Location Recommendation
The next location recommendation is at the core of various location-based applications.
Ranked #1 on
point of interests
on Gowalla
DNN2LR: Interpretation-inspired Feature Crossing for Real-world Tabular Data
Simple classifiers, e. g., Logistic Regression (LR), are globally interpretable, but not powerful enough to model complex nonlinear interactions among features in tabular data.
Deep Active Learning by Model Interpretability
In this paper, inspired by piece-wise linear interpretability in DNN, we introduce the linearly separable regions of samples to the problem of active learning, and propose a novel Deep Active learning approach by Model Interpretability (DAMI).
Simplification of Graph Convolutional Networks: A Matrix Factorization-based Perspective
Moreover, we have also conducted experiments on a typical task of graph embedding, i. e., community detection, and the proposed UCMF model outperforms several representative graph embedding models.
Multifunctional Meta-Optic Systems: Inversely Designed with Artificial Intelligence
Flat optics foresees a new era of ultra-compact optical devices, where metasurfaces serve as the foundation.
An Empirical Study on Feature Discretization
When dealing with continuous numeric features, we usually adopt feature discretization.
Deep Interaction Machine: A Simple but Effective Model for High-order Feature Interactions
IM is an efficient and exact implementation of high-order FM, whose time complexity linearly grows with the order of interactions and the number of feature fields.
Deep Interaction Machine: A Simple but Effective Model for High-order Feature Interactions
IM is an efficient and exact implementation of high-order FM, whose time complexity linearly grows with the order of interactions and the number of feature fields.
Unifying Graph Convolutional Networks as Matrix Factorization
In recent years, substantial progress has been made on graph convolutional networks (GCN).
Automatically Learning Feature Crossing from Model Interpretation for Tabular Data
Automatically feature generation is a major topic of automated machine learning.
CPM-sensitive AUC for CTR prediction
This is because there is a gap between offline AUC and online CPM.
A Generative Model for Inverse Design of Metamaterials
The advent of two-dimensional metamaterials in recent years has ushered in a revolutionary means to manipulate the behavior of light on the nanoscale.
Simulating the Ising Model with a Deep Convolutional Generative Adversarial Network
The deep learning framework is witnessing expansive growth into diverse applications such as biological systems, human cognition, robotics, and the social sciences, thanks to its immense ability to extract essential features from complicated systems.
Disordered Systems and Neural Networks
