Search Results for author:
Found 49 papers, 30 papers with code
Mixed Models with Multiple Instance Learning
Predicting patient features from single-cell data can help identify cellular states implicated in health and disease.
De Novo Drug Design with Joint Transformers
To address this, we propose Joint Transformer that combines a Transformer decoder, Transformer encoder, and a predictor in a joint generative model with shared weights.
Exploring Continual Learning of Diffusion Models
Diffusion models have achieved remarkable success in generating high-quality images thanks to their novel training procedures applied to unprecedented amounts of data.
Discouraging posterior collapse in hierarchical Variational Autoencoders using context
Hierarchical Variational Autoencoders (VAEs) are among the most popular likelihood-based generative models.
Learning Data Representations with Joint Diffusion Models
Joint machine learning models that allow synthesizing and classifying data often offer uneven performance between those tasks or are unstable to train.
Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN
Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data.
Towards a General Purpose CNN for Long Range Dependencies in $N$D
The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learning framework.
On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models
Their main strength comes from their unique setup in which a model (the backward diffusion process) is trained to reverse the forward diffusion process, which gradually adds noise to the input signal.
Alleviating Adversarial Attacks on Variational Autoencoders with MCMC
Variational autoencoders (VAEs) are latent variable models that can generate complex objects and provide meaningful latent representations.
The Effects of Learning in Morphologically Evolving Robot Systems
Simultaneously evolving morphologies (bodies) and controllers (brains) of robots can cause a mismatch between the inherited body and brain in the offspring.
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
In this work, we propose FlexConv, a novel convolutional operation with which high bandwidth convolutional kernels of learnable kernel size can be learned at a fixed parameter cost.
Training Deep Spiking Auto-encoders without Bursting or Dying Neurons through Regularization
In the experiments, we show that applying regularization on membrane potential and spiking output successfully avoids both dead and bursting neurons and significantly decreases the reconstruction error of the spiking auto-encoder.
Storchastic: A Framework for General Stochastic Automatic Differentiation
Stochastic AD extends AD to stochastic computation graphs with sampling steps, which arise when modelers handle the intractable expectations common in Reinforcement Learning and Variational Inference.
Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks
In this work, we explore adversarial attacks on the Variational Autoencoders (VAE).
Invertible DenseNets with Concatenated LipSwish
Furthermore, we propose a learnable weighted concatenation, which not only improves the model performance but also indicates the importance of the concatenated weighted representation.
CKConv: Continuous Kernel Convolution For Sequential Data
Convolutional networks are unable to handle sequences of unknown size and their memory horizon must be defined a priori.
Ranked #5 on
Sequential Image Classification
on Sequential MNIST
General Invertible Transformations for Flow-based Generative Modeling
In this paper, we present a new class of invertible transformations with an application to flow-based generative models.
ABC-Di: Approximate Bayesian Computation for Discrete Data
The obtained results indicate the high potential of the proposed framework and the superiority of the new Markov kernel.
Learning Locomotion Skills in Evolvable Robots
The challenge of robotic reproduction -- making of new robots by recombining two existing ones -- has been recently cracked and physically evolving robot systems have come within reach.
Invertible DenseNets
We introduce Invertible Dense Networks (i-DenseNets), a more parameter efficient alternative to Residual Flows.
Self-Supervised Variational Auto-Encoders
Density estimation, compression and data generation are crucial tasks in artificial intelligence.
Population-based Optimization for Kinetic Parameter Identification in Glycolytic Pathway in Saccharomyces cerevisiae
Models in systems biology are mathematical descriptions of biological processes that are used to answer questions and gain a better understanding of biological phenomena.
Super-resolution Variational Auto-Encoders
The framework of variational autoencoders (VAEs) provides a principled method for jointly learning latent-variable models and corresponding inference models.
Ranked #62 on
Image Generation
on CIFAR-10
(bits/dimension metric)
Wavelet Networks: Scale-Translation Equivariant Learning From Raw Time-Series
In this work, we fill this gap by leveraging the symmetries inherent to time-series for the construction of equivariant neural network.
The Convolution Exponential and Generalized Sylvester Flows
Empirically, we show that the convolution exponential outperforms other linear transformations in generative flows on CIFAR10 and the graph convolution exponential improves the performance of graph normalizing flows.
Time Efficiency in Optimization with a Bayesian-Evolutionary Algorithm
Evolutionary Algorithms (EA) on the other hand rely on search heuristics that typically do not depend on all previous data and can be done in constant time.
Selecting Data Augmentation for Simulating Interventions
We argue that causal concepts can be used to explain the success of data augmentation by describing how they can weaken the spurious correlation between the observed domains and the task labels.
Differential Evolution with Reversible Linear Transformations
Differential evolution (DE) is a well-known type of evolutionary algorithms (EA).
Attentive Group Equivariant Convolutional Networks
Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e. g., relative positions and poses).
Learning Discrete Distributions by Dequantization
Media is generally stored digitally and is therefore discrete.
Learning Directed Locomotion in Modular Robots with Evolvable Morphologies
We generalize the well-studied problem of gait learning in modular robots in two dimensions.
Increasing Expressivity of a Hyperspherical VAE
Learning suitable latent representations for observed, high-dimensional data is an important research topic underlying many recent advances in machine learning.
Video Compression With Rate-Distortion Autoencoders
We employ a model that consists of a 3D autoencoder with a discrete latent space and an autoregressive prior used for entropy coding.
DIVA: Domain Invariant Variational Autoencoders
We consider the problem of domain generalization, namely, how to learn representations given data from a set of domains that generalize to data from a previously unseen domain.
Simulating Execution Time of Tensor Programs using Graph Neural Networks
Optimizing the execution time of tensor program, e. g., a convolution, involves finding its optimal configuration.
DIVA: Domain Invariant Variational Autoencoder
We consider the problem of domain generalization, namely, how to learn representations given data from a set of domains that generalize to data from a previously unseen domain.
Combinatorial Bayesian Optimization using the Graph Cartesian Product
On this combinatorial graph, we propose an ARD diffusion kernel with which the GP is able to model high-order interactions between variables leading to better performance.
Hierarchical VampPrior Variational Fair Auto-Encoder
Decision making is a process that is extremely prone to different biases.
Hyperspherical Variational Auto-Encoders
But although the default choice of a Gaussian distribution for both the prior and posterior represents a mathematically convenient distribution often leading to competitive results, we show that this parameterization fails to model data with a latent hyperspherical structure.
Ranked #6 on
Link Prediction
on Cora
Sylvester Normalizing Flows for Variational Inference
Variational inference relies on flexible approximate posterior distributions.
Attention-based Deep Multiple Instance Learning
Multiple instance learning (MIL) is a variation of supervised learning where a single class label is assigned to a bag of instances.
Ranked #7 on
Aerial Scene Classification
on UCM (50% as trainset)
Deep Learning with Permutation-invariant Operator for Multi-instance Histopathology Classification
The computer-aided analysis of medical scans is a longstanding goal in the medical imaging field.
Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow
In this paper, we propose a new volume-preserving flow and show that it performs similarly to the linear general normalizing flow.
VAE with a VampPrior
In this paper, we propose to extend the variational auto-encoder (VAE) framework with a new type of prior which we call "Variational Mixture of Posteriors" prior, or VampPrior for short.
Improving Variational Auto-Encoders using Householder Flow
One fashion of enriching the variational posterior distribution is application of normalizing flows, i. e., a series of invertible transformations to latent variables with a simple posterior.
Learning Deep Architectures for Interaction Prediction in Structure-based Virtual Screening
We introduce a deep learning architecture for structure-based virtual screening that generates fixed-sized fingerprints of proteins and small molecules by applying learnable atom convolution and softmax operations to each compound separately.
Subspace Restricted Boltzmann Machine
The subspace Restricted Boltzmann Machine (subspaceRBM) is a third-order Boltzmann machine where multiplicative interactions are between one visible and two hidden units.
Prediction of breast cancer recurrence using Classification Restricted Boltzmann Machine with Dropping
In this paper, we apply Classification Restricted Boltzmann Machine (ClassRBM) to the problem of predicting breast cancer recurrence.
Gaussian process regression as a predictive model for Quality-of-Service in Web service systems
In this paper, we present the Gaussian process regression as the predictive model for Quality-of-Service (QoS) attributes in Web service systems.
