Related papers: Semi-supervised Sequential Generative Models
Stochastic control-flow models (SCFMs) are a class of generative models that involve branching on choices from discrete random variables. Amortized gradient-based learning of SCFMs is challenging as most approaches targeting discrete…
Training deep directed graphical models with many hidden variables and performing inference remains a major challenge. Helmholtz machines and deep belief networks are such models, and the wake-sleep algorithm has been proposed to train…
Modeling complex phenomena typically involves the use of both discrete and continuous variables. Such a setting applies across a wide range of problems, from identifying trends in time-series data to performing effective compositional scene…
Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly…
The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the…
A novel class of advanced algorithms, termed Goal-Conditioned Weighted Supervised Learning (GCWSL), has recently emerged to tackle the challenges posed by sparse rewards in goal-conditioned reinforcement learning (RL). GCWSL consistently…
We study a class of neuro-symbolic generative models in which neural networks are used both for inference and as priors over symbolic, data-generating programs. As generative models, these programs capture compositional structures in a…
Reweighted wake-sleep (RWS) is a machine learning method for performing Bayesian inference in a very general class of models. RWS draws $K$ samples from an underlying approximate posterior, then uses importance weighting to provide a better…
Despite their success, convolutional neural networks are computationally expensive because they must examine all image locations. Stochastic attention-based models have been shown to improve computational efficiency at test time, but they…
The currently most prominent algorithm to train keyword spotting (KWS) models with deep neural networks (DNNs) requires strong supervision i.e., precise knowledge of the spoken keyword location in time. Thus, most KWS approaches treat the…
Neural network based generative models with discriminative components are a powerful approach for semi-supervised learning. However, these techniques a) cannot account for model uncertainty in the estimation of the model's discriminative…
Many promising applications of supervised machine learning face hurdles in the acquisition of labeled data in sufficient quantity and quality, creating an expensive bottleneck. To overcome such limitations, techniques that do not depend on…
Deep neural networks for time series must capture complex temporal patterns, to effectively represent dynamic data. Self- and semi-supervised learning methods show promising results in pre-training large models, which -- when finetuned for…
In this paper, we propose a deep invertible hybrid model which integrates discriminative and generative learning at a latent space level for semi-supervised few-shot classification. Various tasks for classifying new species from image data…
We introduce 'semi-unsupervised learning', a problem regime related to transfer learning and zero-shot learning where, in the training data, some classes are sparsely labelled and others entirely unlabelled. Models able to learn from…
We propose Wake-Sleep Consolidated Learning (WSCL), a learning strategy leveraging Complementary Learning System theory and the wake-sleep phases of the human brain to improve the performance of deep neural networks for visual…
Successful Human-Robot collaboration requires a predictive model of human behavior. The robot needs to be able to recognize current goals and actions and to predict future activities in a given context. However, the spatio-temporal sequence…
Supervised learning, characterized by both discriminative and generative learning, seeks to predict the values of single (or sometimes multiple) predefined target attributes based on a predefined set of predictor attributes. For…
Weakly supervised object detection has recently received much attention, since it only requires image-level labels instead of the bounding-box labels consumed in strongly supervised learning. Nevertheless, the save in labeling expense is…
Semi-supervised learning plays an important role in large-scale machine learning. Properly using additional unlabeled data (largely available nowadays) often can improve the machine learning accuracy. However, if the machine learning model…