We survey recent work on neurosymbolic programming, an emerging area that bridges the
areas of deep learning and program synthesis. Like in classic machine learning, the goal …

Deep reinforcement learning (RL) has led to encouraging successes in many challenging
control tasks. However, a deep RL model lacks interpretability due to the difficulty of …

Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific
discovery. These models combine neural and symbolic components to learn complex …

The discovery of neural architectures from simple building blocks is a long-standing goal of
Neural Architecture Search (NAS). Hierarchical search spaces are a promising step towards …

Efficient and automated design of optimizers plays a crucial role in full-stack AutoML
systems. However, prior methods in optimizer search are often limited by their scalability …

We develop techniques for synthesizing neurosymbolic programs. Such programs mix
discrete symbolic processing with continuous neural computation. We relax this mixed …

There is an increasing interest in the area of quantum computing but developing quantum
algorithms is difficult. Neural Network augmented search algorithms have proven quite …

We present a framework for the unsupervised learning of neurosymbolic encoders, which
are encoders obtained by composing neural networks with symbolic programs from a …

The discovery of neural architectures from scratch is the long-standing goal of Neural
Architecture Search (NAS). Searching over a wide spectrum of neural architectures can …

Physics-informed Neural Networks (PINNs) have been widely used to obtain accurate
neural surrogates for a system of Partial Differential Equations (PDE). One of the major …