We present a simple enhancement of CP (which we call SimplE) to allow the two embeddings of each entity to be learned dependently. The complexity of SimplE grows linearly with the size of embeddings.

Neural Information Processing Systems http://nips.cc/

We present a novel approach to probabilistic time series forecasting that combines state space models with deep learning. By parametrizing a per-time-series linear state space model with a jointly-learned recurrent neural network, our method retains desired properties of state space models such as data efficiency and inter-pretability, while making use of the ability to learn complex patterns from raw data offered by deep learning approaches. Our method scales gracefully from regimes where little training data is available to regimes where data from large collection of time series can be leveraged to learn accurate models. We provide qualitative as well as quantitative results with the proposed method, showing that it compares favorably to the state-of-the-art.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Pgx is available at https://github.com/sotetsuk/pgx. Figure 1: Example games included in Pgx.

This paper questions the effectiveness of a modern predictive uncertainty quantification approach, called evidential deep learning (EDL), in which a single neural network model is trained to learn a meta distribution over the predictive distribution by minimizing a specific objective function.

In Tab. 1, we provide a comprehensive summary of the general notations used throughout the paper Definition B.1 (Quasi-isometric Properties), Let Definition B.2 (Local Quasi-isometric Properties), Local quasi-isometry refers to a function whereby The proposed quasi-isometric loss benefits from the incorporation of a local distance-preserving condition. In Tab. 2, we report We elaborate on the specifics of the experimental setup in Tab. 3. We impose our quasi-isometric loss and object-wise depth map loss using the output feature extracted from DLAUp. This extracted object descriptor is subsequently utilized to compute the loss. We provide additional qualitative results using the MonoCon and "MonoCon + Ours" as discussed Tab. Geometry uncertainty projection network for monocular 3d object detection.

Data-driven methods for electrocardiogram (ECG) interpretation are rapidly progressing. Large datasets have enabled advances in artificial intelligence (AI) based ECG analysis, yet limitations in annotation quality, size, and scope remain major challenges. Here we present CODE-II, a large-scale real-world dataset of 2,735,269 12-lead ECGs from 2,093,807 adult patients collected by the Telehealth Network of Minas Gerais (TNMG), Brazil. Each exam was annotated using standardized diagnostic criteria and reviewed by cardiologists. A defining feature of CODE-II is a set of 66 clinically meaningful diagnostic classes, developed with cardiologist input and routinely used in telehealth practice. We additionally provide an open available subset: CODE-II-open, a public subset of 15,000 patients, and the CODE-II-test, a non-overlapping set of 8,475 exams reviewed by multiple cardiologists for blinded evaluation. A neural network pre-trained on CODE-II achieved superior transfer performance on external benchmarks (PTB-XL and CPSC 2018) and outperformed alternatives trained on larger datasets.

We present a class of algorithms for state estimation in nonlinear, non-Gaussian state-space models. Our approach is based on a variational Lagrangian formulation that casts Bayesian inference as a sequence of entropic trust-region updates subject to dynamic constraints. This framework gives rise to a family of forward-backward algorithms, whose structure is determined by the chosen factorization of the variational posterior. By focusing on Gauss--Markov approximations, we derive recursive schemes with favorable computational complexity. For general nonlinear, non-Gaussian models we close the recursions using generalized statistical linear regression and Fourier--Hermite moment matching.