Deep Learning
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Playing text-based games requires skills in processing natural language and sequential decision making.
Exploring Models and Data for Image Question Answering
Mengye Ren, Ryan Kiros, Richard Zemel
This work aims to address the problem of image-based question-answering (QA) with new models and datasets. In our work, we propose to use neural networks and visual semantic embeddings, without intermediate stages such as object detection and image segmentation, to predict answers to simple questions about images. Our model performs 1.8 times better than the only published results on an existing image QA dataset. We also present a question generation algorithm that converts image descriptions, which are widely available, into QA form. We used this algorithm to produce an order-of-magnitude larger dataset, with more evenly distributed answers. A suite of baseline results on this new dataset are also presented.
Learning to summarize from human feedback Nisan Stiennon Long Ouyang Jeff Wu
As language models become more powerful, training and evaluation are increasingly bottlenecked by the data and metrics used for a particular task.
Normalizing Kalman Filters for Multivariate Time Series Analysis Emmanuel de Bรฉzenac
This paper tackles the modelling of large, complex and multivariate time series panels in a probabilistic setting. To this extent, we present a novel approach reconciling classical state space models with deep learning methods.
Normalizing Kalman Filters for Multivariate Time Series Analysis Emmanuel de Bรฉzenac
This paper tackles the modelling of large, complex and multivariate time series panels in a probabilistic setting. To this extent, we present a novel approach reconciling classical state space models with deep learning methods.
Adversarial Self-Supervised Contrastive Learning Minseon Kim
In this paper, we propose a novel adversarial attack for unlabeled data, which makes the model confuse the instance-level identities of the perturbed data samples. Further, we present a self-supervised contrastive learning framework to adversarially train a robust neural network without labeled data, which aims to maximize the similarity between a random augmentation of a data sample and its instance-wise adversarial perturbation.
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
We propose to use line-search techniques to automatically set the step-size when training models that can interpolate the data.
Modeling Tabular data using Conditional GAN
Lei Xu, Maria Skoularidou, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
Recent developments in deep generative models have led to a wealth of possibilities.