Search Results for author:
Found 40 papers, 10 papers with code
Stability Analysis of Various Symbolic Rule Extraction Methods from Recurrent Neural Network
We sampled the datasets from $7$ Tomita and $4$ Dyck grammars and trained them on $4$ RNN cells: LSTM, GRU, O2RNN, and MIRNN.
Estimating Uncertainty in Landslide Segmentation Models
Landslides are a recurring, widespread hazard.
On the Computational Complexity and Formal Hierarchy of Second Order Recurrent Neural Networks
In this work, we extend the theoretical foundation for the $2^{nd}$-order recurrent network ($2^{nd}$ RNN) and prove there exists a class of a $2^{nd}$ RNN that is Turing-complete with bounded time.
An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions
Noisy marginals are a common form of confidentiality-protecting data release and are useful for many downstream tasks such as contingency table analysis, construction of Bayesian networks, and even synthetic data generation.
Differentiable modeling to unify machine learning and physical models and advance Geosciences
Here we present differentiable geoscientific modeling as a powerful pathway toward dissolving the perceived barrier between them and ushering in a paradigm shift.
Answering Private Linear Queries Adaptively using the Common Mechanism
Since M* will be used no matter what, the analyst can use its output to decide whether to subsequently run M1'(thus recreating the analysis supported by M1) or M2'(recreating the analysis supported by M2), without wasting privacy loss budget.
PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization
Given the logit scores produced by the base segmentation model, each pixel is given a pseudo-label that is obtained by optimally thresholding the logit scores in each image patch.
Ranked #1 on
Few-Shot Semantic Segmentation
on FSS-1000 (5-shot)
(mIoU metric)
Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder
In light of this, we propose a system that learns to improve the encoding performance by enhancing its internal neural representations on both the encoder and decoder ends, an approach we call Neural JPEG.
An Empirical Analysis of Recurrent Learning Algorithms In Neural Lossy Image Compression Systems
Recent advances in deep learning have resulted in image compression algorithms that outperform JPEG and JPEG 2000 on the standard Kodak benchmark.
OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas
A common approach has been to use standard convolutional networks to predict the corners and boundaries, followed by post-processing to generate the 3D layout.
Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units
Two particular tasks that test this type of reasoning are (1) mathematical equation verification, which requires determining whether trigonometric and linear algebraic statements are valid identities or not, and (2) equation completion, which entails filling in a blank within an expression to make it true.
The data synergy effects of time-series deep learning models in hydrology
We hypothesize that DL models automatically adjust their internal representations to identify commonalities while also providing sufficient discriminatory information to the model.
The Neural Coding Framework for Learning Generative Models
Neural generative models can be used to learn complex probability distributions from data, to sample from them, and to produce probability density estimates.
Optimizing Fitness-For-Use of Differentially Private Linear Queries
In practice, differentially private data releases are designed to support a variety of applications.
Databases
Differentially Private Deep Learning with Direct Feedback Alignment
Standard methods for differentially private training of deep neural networks replace back-propagated mini-batch gradients with biased and noisy approximations to the gradient.
Scaling up Differentially Private Deep Learning with Fast Per-Example Gradient Clipping
The reason for this slowdown is a crucial privacy-related step called "per-example gradient clipping" whose naive implementation undoes the benefits of batch training with GPUs.
CheckDP: An Automated and Integrated Approach for Proving Differential Privacy or Finding Precise Counterexamples
We propose CheckDP, the first automated and integrated approach for proving or disproving claims that a mechanism is differentially private.
Programming Languages D.3.1
Recognizing Long Grammatical Sequences Using Recurrent Networks Augmented With An External Differentiable Stack
In this paper, we improve the memory-augmented RNN with important architectural and state updating mechanisms that ensure that the model learns to properly balance the use of its latent states with external memory.
Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment
Training deep neural networks on large-scale datasets requires significant hardware resources whose costs (even on cloud platforms) put them out of reach of smaller organizations, groups, and individuals.
Evaluating aleatoric and epistemic uncertainties of time series deep learning models for soil moisture predictions
Soil moisture is an important variable that determines floods, vegetation health, agriculture productivity, and land surface feedbacks to the atmosphere, etc.
Lifelong Neural Predictive Coding: Learning Cumulatively Online without Forgetting
In lifelong learning systems based on artificial neural networks, one of the biggest obstacles is the inability to retain old knowledge as new information is encountered.
Free Gap Information from the Differentially Private Sparse Vector and Noisy Max Mechanisms
We show that it can also release for free the noisy gap between the approximate maximizer and runner-up.
Proving Differential Privacy with Shadow Execution
Sometimes, combining those two requires substantial changes to program logics: one recent paper is able to verify Report Noisy Max automatically, but it involves a complex verification system using customized program logics and verifiers.
Programming Languages D.2.4
Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations
We compare our model and learning procedure to other back-propagation through time alternatives (which also tend to be computationally expensive), including real-time recurrent learning, echo state networks, and unbiased online recurrent optimization.
ET-Lasso: A New Efficient Tuning of Lasso-type Regularization for High-Dimensional Data
The pseudo-features are constructed to be inactive by nature, which can be used to obtain a cutoff to select the tuning parameter that separates active and inactive features.
TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade
We propose a novel and effective framework for this and experimentally demonstrate that: (1) A CNN that can be effectively used to extract instance-level text contour from natural images.
Concentrated Differentially Private Gradient Descent with Adaptive per-Iteration Privacy Budget
It outperforms prior algorithms for model fitting and is competitive with the state-of-the-art for $(\epsilon,\delta)$-differential privacy, a strictly weaker definition than zCDP.
Detecting Outliers in Data with Correlated Measures
Advances in sensor technology have enabled the collection of large-scale datasets.
Toward Detecting Violations of Differential Privacy
The widespread acceptance of differential privacy has led to the publication of many sophisticated algorithms for protecting privacy.
Cryptography and Security
Large Scale Scene Text Verification with Guided Attention
In this work, we propose a new framework that learns this task in an end-to-end way.
Adversarial Training for Community Question Answer Selection Based on Multi-scale Matching
We frame this task as a binary (relevant/irrelevant) classification problem, and present an adversarial training framework to alleviate label imbalance issue.
Differentially Private Confidence Intervals for Empirical Risk Minimization
The process of data mining with differential privacy produces results that are affected by two types of noise: sampling noise due to data collection and privacy noise that is designed to prevent the reconstruction of sensitive information.
Conducting Credit Assignment by Aligning Local Representations
Using back-propagation and its variants to train deep networks is often problematic for new users.
Prolongation of SMAP to Spatio-temporally Seamless Coverage of Continental US Using a Deep Learning Neural Network
The Soil Moisture Active Passive (SMAP) mission has delivered valuable sensing of surface soil moisture since 2015.
Multi-Scale FCN With Cascaded Instance Aware Segmentation for Arbitrary Oriented Word Spotting in the Wild
Scene text detection has attracted great attention these years.
Learning to Extract Semantic Structure From Documents Using Multimodal Fully Convolutional Neural Networks
We present an end-to-end, multimodal, fully convolutional network for extracting semantic structures from document images.
Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network
We present an end-to-end, multimodal, fully convolutional network for extracting semantic structures from document images.
Predicting Demographics of High-Resolution Geographies with Geotagged Tweets
For the task of predicting gender and race/ethnicity counts at the blockgroup-level, an approach adapted from prior work to our problem achieves an average correlation of 0. 389 (gender) and 0. 569 (race) on a held-out test dataset.
A New Class of Private Chi-Square Tests
In this paper, we develop new test statistics for private hypothesis testing.
Statistics Theory Cryptography and Security Statistics Theory
Unifying Adversarial Training Algorithms with Flexible Deep Data Gradient Regularization
Many previous proposals for adversarial training of deep neural nets have included di- rectly modifying the gradient, training on a mix of original and adversarial examples, using contractive penalties, and approximately optimizing constrained adversarial ob- jective functions.
