Search Results for author:
Found 47 papers, 13 papers with code
Modified Baum-Welch Algorithm for Joint Blind Channel Estimation and Turbo Equalization
This modification enables us to reduce the number of required states by half while maintaining the same performance.
Robust Training Objectives Improve Embedding-based Retrieval in Industrial Recommendation Systems
In light of these two challenges, we evaluate using a robust training objective, specifically SSMTL, through a large-scale friend recommendation system on a social media platform in the tech sector, identifying whether this increase in robustness can work at scale in enhancing retrieval in the production setting.
PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis
We present a comprehensive framework for predicting the effects of perturbations in single cells, designed to standardize benchmarking in this rapidly evolving field.
Analysis of Impulsive Interference in Digital Audio Broadcasting Systems in Electric Vehicles
Recently, new types of interference in electric vehicles (EVs), such as converters switching and/or battery chargers, have been found to degrade the performance of wireless digital transmission systems.
Data-Driven Symbol Detection for Intersymbol Interference Channels with Bursty Impulsive Noise
In addition to detection over the joint ISI and IN states we also focused on another scenario where trellis transitions are not trivial: detection for the ISI channel with AWGN with inaccurate knowledge of the channel memory at the receiver.
CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer for Object Detection under Unknown Degradations
Object detection methods under known single degradations have been extensively investigated.
Multi-perspective Feedback-attention Coupling Model for Continuous-time Dynamic Graphs
Recently, representation learning over graph networks has gained popularity, with various models showing promising results.
Dynamic Link Prediction for New Nodes in Temporal Graph Networks
To overcome the few-shot challenge, we incorporate the encoder-predictor into the meta-learning paradigm, which can learn two types of implicit information during the formation of the temporal network through span adaptation and node adaptation.
AbDiffuser: Full-Atom Generation of in vitro Functioning Antibodies
We introduce AbDiffuser, an equivariant and physics-informed diffusion model for the joint generation of antibody 3D structures and sequences.
Protein Discovery with Discrete Walk-Jump Sampling
We resolve difficulties in training and sampling from a discrete generative model by learning a smoothed energy function, sampling from the smoothed data manifold with Langevin Markov chain Monte Carlo (MCMC), and projecting back to the true data manifold with one-step denoising.
Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Tasks
Our proposed method involves utilizing a technique known as knowledge distillation, in which a pre-trained ``teacher'' policy trained with multiple camera viewpoints guides a ``student'' policy in learning from a single camera viewpoint.
On a continuous time model of gradient descent dynamics and instability in deep learning
The recipe behind the success of deep learning has been the combination of neural networks and gradient-based optimization.
AI Enabled Maneuver Identification via the Maneuver Identification Challenge
Artificial intelligence (AI) has enormous potential to improve Air Force pilot training by providing actionable feedback to pilot trainees on the quality of their maneuvers and enabling instructor-less flying familiarization for early-stage trainees in low-cost simulators.
Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racing
The resulting policy directly infers control commands with feature representations learned from raw images, forgoing the need for globally-consistent state estimation, trajectory planning, and handcrafted control design.
A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences
Deep generative models have emerged as a popular machine learning-based approach for inverse design problems in the life sciences.
Multi-frequency PolSAR Image Fusion Classification Based on Semantic Interactive Information and Topological Structure
Finally, an adaptive weighting fusion (AWF) strategy is proposed to merge inference from different bands, so as to make the MF joint classification decisions of SIC and TPC.
The least-used key selection method for information retrieval in large-scale Cloud-based service repositories
The experimental results show that the proposed least-used key selection method improves the service retrieval efficiency significantly compared with the designated key selection method in the case of the unequal appearing probability of parameters in service retrieval requests under three indexing models.
TAILOR: Teaching with Active and Incremental Learning for Object Registration
When deploying a robot to a new task, one often has to train it to detect novel objects, which is time-consuming and labor-intensive.
CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
This is mainly because the correlation volume, the basis of pixel matching, is computed as the dot product of the convolutional features of the two images.
Ranked #9 on
Optical Flow Estimation
on KITTI 2015 (train)
End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation
The proposed method learns keypoints from camera images as the state representation, through a self-supervised autoencoder architecture.
SAGA: Stochastic Whole-Body Grasping with Contact
Given an initial pose and the generated whole-body grasping pose as the start and end of the motion respectively, we design a novel contact-aware generative motion infilling module to generate a diverse set of grasp-oriented motions.
Optimization of Service Addition in Multilevel Index Model for Edge Computing
With the development of Edge Computing and Artificial Intelligence (AI) technologies, edge devices are witnessed to generate data at unprecedented volume.
Discretization Drift in Two-Player Games
Gradient-based methods for two-player games produce rich dynamics that can solve challenging problems, yet can be difficult to stabilize and understand.
A Feature Fusion-Net Using Deep Spatial Context Encoder and Nonstationary Joint Statistical Model for High Resolution SAR Image Classification
To address this problem, a novel end-to-end supervised classification method is proposed for HR SAR images by considering both spatial context and statistical features.
Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory
Episodic and semantic memory are critical components of the human memory model.
Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution
Modern solutions to the single image super-resolution (SISR) problem using deep neural networks aim not only at better performance accuracy but also at a lighter and computationally efficient model.
Training Generative Adversarial Networks by Solving Ordinary Differential Equations
From this perspective, we hypothesise that instabilities in training GANs arise from the integration error in discretising the continuous dynamics.
Neural Architecture Search of SPD Manifold Networks
To address this problem, we first introduce a geometrically rich and diverse SPD neural architecture search space for an efficient SPD cell design.
Dense Dual-Path Network for Real-time Semantic Segmentation
We design a light-weight and powerful backbone with dense connectivity to facilitate feature reuse throughout the whole network and the proposed Dual-Path module (DPM) to sufficiently aggregate multi-scale contexts.
Neural Architecture Search as Sparse Supernet
This paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-Path and Multi-Path Search to automated Mixed-Path Search.
Product Kanerva Machines: Factorized Bayesian Memory
An ideal cognitively-inspired memory system would compress and organize incoming items.
Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning
The proposed method is able to efficiently generalize the previously learned task by model fusion to solve the environment adaptation problem.
LOGAN: Latent Optimisation for Generative Adversarial Networks
Training generative adversarial networks requires balancing of delicate adversarial dynamics.
Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Network
CV-FCN employs a complex downsampling-then-upsampling scheme to extract dense features.
6D Pose Estimation with Correlation Fusion
To our best knowledge, this is the first work to explore effective intra- and inter-modality fusion in 6D pose estimation.
Real-time Multi-target Path Prediction and Planning for Autonomous Driving aided by FCN
Real-time multi-target path planning is a key issue in the field of autonomous driving.
U-net super-neural segmentation and similarity calculation to realize vegetation change assessment in satellite imagery
Vegetation is the natural linkage connecting soil, atmosphere and water.
Shaping Belief States with Generative Environment Models for RL
We propose a way to efficiently train expressive generative models in complex environments.
Deep Compressed Sensing
CS is flexible and data efficient, but its application has been restricted by the strong assumption of sparsity and costly reconstruction process.
Learning Attractor Dynamics for Generative Memory
Based on the idea of memory writing as inference, as proposed in the Kanerva Machine, we show that a likelihood-based Lyapunov function emerges from maximising the variational lower-bound of a generative memory.
Optimizing Agent Behavior over Long Time Scales by Transporting Value
Humans spend a remarkable fraction of waking life engaged in acts of "mental time travel".
DFNet: Semantic Segmentation on Panoramic Images with Dynamic Loss Weights and Residual Fusion Block
We propose the DFNet and make two main contributions, one is dynamic loss weights, and the other is residual fusion block (RFB).
VH-HFCN based Parking Slot and Lane Markings Segmentation on Panoramic Surround View
At the same time, we proposed a highly fused convolutional network (HFCN) based segmentation method for parking slot and lane markings based on the PSV dataset.
The Kanerva Machine: A Generative Distributed Memory
We present an end-to-end trained memory system that quickly adapts to new data and generates samples like them.
Semantic Segmentation via Highly Fused Convolutional Network with Multiple Soft Cost Functions
We evaluate our model on three major segmentation datasets: CamVid, PASCAL VOC and ADE20K.
Contractive De-noising Auto-encoder
Auto-encoder is a special kind of neural network based on reconstruction.
Spectral Classification Using Restricted Boltzmann Machine
The algorithm is applied for the spectral classification in astronomy.
