Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Maene, Jaron"'
A popular approach to neurosymbolic AI involves mapping logic formulas to arithmetic circuits (computation graphs consisting of sums and products) and passing the outputs of a neural network through these circuits. This approach enforces symbolic con
Externí odkaz:
http://arxiv.org/abs/2410.11415
Autor:
Adriaensen, Rik, Maene, Jaron
Fueled by the popularity of the transformer architecture in deep learning, several works have investigated what formal languages a transformer can learn. Nonetheless, existing results remain hard to compare and a fine-grained understanding of the tra
Externí odkaz:
http://arxiv.org/abs/2410.06045
The limitations of purely neural learning have sparked an interest in probabilistic neurosymbolic models, which combine neural networks with probabilistic logical reasoning. As these neurosymbolic models are trained with gradient descent, we study th
Externí odkaz:
http://arxiv.org/abs/2406.04472
The lottery ticket hypothesis states that sparse subnetworks exist in randomly initialized dense networks that can be trained to the same accuracy as the dense network they reside in. However, the subsequent work has failed to replicate this on large
Externí odkaz:
http://arxiv.org/abs/2106.06955
Autor:
Agarwal, Mayank, Chakraborti, Tathagata, Fu, Quchen, Gros, David, Lin, Xi Victoria, Maene, Jaron, Talamadupula, Kartik, Teng, Zhongwei, White, Jules
The NLC2CMD Competition hosted at NeurIPS 2020 aimed to bring the power of natural language processing to the command line. Participants were tasked with building models that can transform descriptions of command line tasks in English to their Bash s
Externí odkaz:
http://arxiv.org/abs/2103.02523