Search Results for author:
Found 24 papers, 10 papers with code
Molecule-Edit Templates for Efficient and Accurate Retrosynthesis Prediction
Retrosynthesis involves determining a sequence of reactions to synthesize complex molecules from simpler precursors.
An efficient deep neural network to find small objects in large 3D images
On a dataset collected at NYU Langone Health, including 85, 526 patients with full-field 2D mammography (FFDM), synthetic 2D mammography, and 3D mammography, 3D-GMIC achieves an AUC of 0. 831 (95% CI: 0. 769-0. 887) in classifying breasts with malignant findings using 3D mammography.
Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
We propose an algorithm to balance the conditional learning speeds between modalities during training and demonstrate that it indeed addresses the issue of greedy learning.
Relative Molecule Self-Attention Transformer
Self-supervised learning holds promise to revolutionize molecule property prediction - a central task to drug discovery and many more industries - by enabling data efficient learning from scarce experimental data.
RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
A natural idea to mitigate this problem is to bias the search process towards more easily synthesizable molecules using a proxy for synthetic accessibility.
Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks
By training neural networks on these adversarial examples, we can improve their generalisation in collider bias settings.
An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department
In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time.
Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits
The central challenge in automated synthesis planning is to be able to generate and predict outcomes of a diverse set of chemical reactions.
Ranked #9 on
Single-step retrosynthesis
on USPTO-50k
Understanding the robustness of deep neural network classifiers for breast cancer screening
Deep neural networks (DNNs) show promise in breast cancer screening, but their robustness to input perturbations must be better understood before they can be clinically implemented.
Molecule Attention Transformer
Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug discovery industry.
Improving the Ability of Deep Neural Networks to Use Information From Multiple Views in Breast Cancer Screening
In breast cancer screening, radiologists make the diagnosis based on images that are taken from two angles.
Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift
Recent work has shown that using unlabeled data in semi-supervised learning is not always beneficial and can even hurt generalization, especially when there is a class mismatch between the unlabeled and labeled examples.
Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
We present a deep convolutional neural network for breast cancer screening exam classification, trained and evaluated on over 200, 000 exams (over 1, 000, 000 images).
Non-linear ICA based on Cramer-Wold metric
Non-linear source separation is a challenging open problem with many applications.
Neural Architecture Search Over a Graph Search Space
However, the success of NAS depends on the definition of the search space.
Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function
We propose that in ResNets this can be resolved based on our results, by ensuring the same level of dynamical isometry at initialization.
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
When studying the SGD dynamics in relation to the sharpest directions in this initial phase, we find that the SGD step is large compared to the curvature and commonly fails to minimize the loss along the sharpest directions.
Cramer-Wold AutoEncoder
The crucial new ingredient is the introduction of a new (Cramer-Wold) metric in the space of densities, which replaces the Wasserstein metric used in SWAE.
Commonsense mining as knowledge base completion? A study on the impact of novelty
Commonsense knowledge bases such as ConceptNet represent knowledge in the form of relational triples.
Three Factors Influencing Minima in SGD
In particular we find that the ratio of learning rate to batch size is a key determinant of SGD dynamics and of the width of the final minima, and that higher values of the ratio lead to wider minima and often better generalization.
Residual Connections Encourage Iterative Inference
In general, a Resnet block tends to concentrate representation learning behavior in the first few layers while higher layers perform iterative refinement of features.
A Closer Look at Memorization in Deep Networks
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness.
Learning to Compute Word Embeddings On the Fly
Words in natural language follow a Zipfian distribution whereby some words are frequent but most are rare.
Ranked #48 on
Question Answering
on SQuAD1.1 dev
Learning to SMILE(S)
This paper shows how one can directly apply natural language processing (NLP) methods to classification problems in cheminformatics.
