Alvin Wan
YOU?
Author Swipe
View article: EAGLE-AI: A large language model workflow for automated extraction and scoring of literature evidence linking genes to autism spectrum disorder
EAGLE-AI: A large language model workflow for automated extraction and scoring of literature evidence linking genes to autism spectrum disorder Open
We previously developed the Evaluation of Autism Gene Link Evidence (EAGLE) manual curation framework and used it to characterise 219 autism-associated genes. However, this effort took years of human work. We present EAGLE-AI, an automated…
View article: Development of an Open-Source Software Tool for Microstructure Analysis of Materials Using Artificial Intelligence
Development of an Open-Source Software Tool for Microstructure Analysis of Materials Using Artificial Intelligence Open
Investigating the microstructures of materials with microscopy is a key task in quality assurance, the development of new materials, and the optimization of manufacturing processes. However, conventional image analysis often demands signif…
View article: CathAI: fully automated coronary angiography interpretation and stenosis estimation
CathAI: fully automated coronary angiography interpretation and stenosis estimation Open
Coronary angiography is the primary procedure for diagnosis and management decisions in coronary artery disease (CAD), but ad-hoc visual assessment of angiograms has high variability. Here we report a fully automated approach to interpret …
View article: UPSCALE: Unconstrained Channel Pruning
UPSCALE: Unconstrained Channel Pruning Open
As neural networks grow in size and complexity, inference speeds decline. To combat this, one of the most effective compression techniques -- channel pruning -- removes channels from weights. However, for multi-branch segments of a model, …
View article: AutoFocusFormer: Image Segmentation off the Grid
AutoFocusFormer: Image Segmentation off the Grid Open
Real world images often have highly imbalanced content density. Some areas are very uniform, e.g., large patches of blue sky, while other areas are scattered with many small objects. Yet, the commonly used successive grid downsampling stra…
View article: CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks
CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks Open
Coronary heart disease (CHD) is the leading cause of adult death in the United States and worldwide, and for which the coronary angiography procedure is the primary gateway for diagnosis and clinical management decisions. The standard-of-c…
View article: SegNBDT: Visual Decision Rules for Segmentation
SegNBDT: Visual Decision Rules for Segmentation Open
The black-box nature of neural networks limits model decision interpretability, in particular for high-dimensional inputs in computer vision and for dense pixel prediction tasks like segmentation. To address this, prior work combines neura…
View article: Visual Transformers: Token-based Image Representation and Processing for Computer Vision
Visual Transformers: Token-based Image Representation and Processing for Computer Vision Open
Computer vision has achieved remarkable success by (a) representing images as uniformly-arranged pixel arrays and (b) convolving highly-localized features. However, convolutions treat all image pixels equally regardless of importance; expl…
View article: FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function
FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function Open
Neural Architecture Search (NAS) yields state-of-the-art neural networks that outperform their best manually-designed counterparts. However, previous NAS methods search for architectures under one training recipe (i.e., training hyperparam…
View article: FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining
FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining Open
Neural Architecture Search (NAS) yields state-of-the-art neural networks that outperform their best manually-designed counterparts. However, previous NAS methods search for architectures under one set of training hyper-parameters (i.e., a …
View article: FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions Open
Differentiable Neural Architecture Search (DNAS) has demonstrated great success in designing state-of-the-art, efficient neural networks. However, DARTS-based DNAS's search space is small when compared to other search methods', since all c…
View article: NBDT: Neural-Backed Decision Trees
NBDT: Neural-Backed Decision Trees Open
Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use. In response, previous work combines decision trees with deep learning, yielding models tha…
View article: Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning
Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning Open
Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagine…
View article: Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions Open
Neural networks rely on convolutions to aggregate spatial information. However, spatial convolutions are expensive in terms of model size and computation, both of which grow quadratically with respect to kernel size. In this paper, we pres…
View article: SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud Open
In this paper, we address semantic segmentation of road-objects from 3D LiDAR point clouds. In particular, we wish to detect and categorize instances of interest, such as cars, pedestrians and cyclists. We formulate this problem as a point…
View article: SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving Open
Object detection is a crucial task for autonomous driving. In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires real-time inference speed to guarantee prompt vehicle control, as wel…