Here, we introduce ViRel, a method for unsupervised discovery and learning of Visual Relations with graph-level analogy.
In this work, we introduce Zero-shot Concept Recognition and Acquisition (ZeroC), a neuro-symbolic architecture that can recognize and acquire novel concepts in a zero-shot way.
To model complex reservoir dynamics at both local and global scale, HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure.
We test our method in a 1D benchmark of nonlinear PDEs, 2D Navier-Stokes flows into turbulent phase and an inverse optimization of boundary conditions in 2D Navier-Stokes flow.
We design two sampling algorithms for structural regularization and instantiate the GIB principle with two new models: GIB-Cat and GIB-Bern, and demonstrate the benefits by evaluating the resilience to adversarial attacks.
We present an improved method for symbolic regression that seeks to fit data to formulas that are Pareto-optimal, in the sense of having the best accuracy for a given complexity.
Firstly, how can we make the learning models more flexible and efficient, so that agents can learn quickly with fewer examples?
In the Information Bottleneck (IB), when tuning the relative strength between compression and prediction terms, how do the two terms behave, and what's their relationship with the dataset and the learned representation?
Identifying the underlying directional relations from observational time series with nonlinear interactions and complex relational structures is key to a wide range of applications, yet remains a hard problem.
The goal of lossy data compression is to reduce the storage cost of a data set $X$ while retaining as much information as possible about something ($Y$) that you care about.
However, in practice, not only is $\beta$ chosen empirically without theoretical guidance, there is also a lack of theoretical understanding between $\beta$, learnability, the intrinsic nature of the dataset and model capacity.
Learning causal relations from observational time series with nonlinear interactions and complex causal structures is a key component of human intelligence, and has a wide range of applications.
We investigate opportunities and challenges for improving unsupervised machine learning using four common strategies with a long history in physics: divide-and-conquer, Occam's razor, unification and lifelong learning.
Compared to humans, machine learning models generally require significantly more training examples and fail to extrapolate from experience to solve previously unseen challenges.
To highlight, RP with a CNN classifier can predict if an MNIST digit is a "one"or "not" with only 0. 25% error, and 0. 46 error across all digits, even when 50% of positive examples are mislabeled and 50% of observed positive labels are mislabeled negative examples.