相关论文: Event Representation with Sequential, Semi-Supervi…

Semantically meaningful information content in perceptual signals is usually unevenly distributed. In speech signals for example, there are often many silences, and the speed of pronunciation can vary considerably. In this work, we propose…

Estimating the parameters of a model describing a set of observations using a neural network is in general solved in a supervised way. In cases when we do not have access to the model's true parameters this approach can not be applied.…

Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We…

Categorical variables are a natural choice for representing discrete structure in the world. However, stochastic neural networks rarely use categorical latent variables due to the inability to backpropagate through samples. In this work, we…

We propose a sequential variational autoencoder to learn disentangled representations of sequential data (e.g., videos and audios) under self-supervision. Specifically, we exploit the benefits of some readily accessible supervisory signals…

Self-training is an effective approach to semi-supervised learning. The key idea is to let the learner itself iteratively generate "pseudo-supervision" for unlabeled instances based on its current hypothesis. In combination with consistency…

Despite the frequent use of agent-based models (ABMs) for studying social phenomena, parameter estimation remains a challenge, often relying on costly simulation-based heuristics. This work uses variational inference to estimate the…

Event-based cameras are dynamic vision sensors that provide asynchronous measurements of changes in per-pixel brightness at a microsecond level. This makes them significantly faster than conventional frame-based cameras, and an appealing…

Event cameras asynchronously capture brightness changes with low latency, high temporal resolution, and high dynamic range. However, annotation of event data is a costly and laborious process, which limits the use of deep learning methods…

In this work, we propose a novel framework for unsupervised learning for event cameras that learns motion information from only the event stream. In particular, we propose an input representation of the events in the form of a discretized…

Numerous models for supervised and reinforcement learning benefit from combinations of discrete and continuous model components. End-to-end learnable discrete-continuous models are compositional, tend to generalize better, and are more…

In recent years, discriminative self-supervised methods have made significant strides in advancing various visual tasks. The central idea of learning a data encoder that is robust to data distortions/augmentations is straightforward yet…

The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled. Most approaches to disentanglement rely on continuous variables, both for…

Accurately modeling robot dynamics is crucial to safe and efficient motion control. In this paper, we develop and apply an iterative learning semi-parametric model, with a neural network, to the task of autonomous racing with a Model…

This paper presents SPeCiaL: a method for unsupervised pretraining of representations tailored for continual learning. Our approach devises a meta-learning objective that differentiates through a sequential learning process. Specifically,…

Event cameras are novel vision sensors that sample, in an asynchronous fashion, brightness increments with low latency and high temporal resolution. The resulting streams of events are of high value by themselves, especially for high speed…

We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing.…

Variational approximations are increasingly based on gradient-based optimization of expectations estimated by sampling. Handling discrete latent variables is then challenging because the sampling process is not differentiable. Continuous…

Structured latent variables allow incorporating meaningful prior knowledge into deep learning models. However, learning with such variables remains challenging because of their discrete nature. Nowadays, the standard learning approach is to…

In this work we explore deep generative models of text in which the latent representation of a document is itself drawn from a discrete language model distribution. We formulate a variational auto-encoder for inference in this model and…