7 papers · 1 filter
Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning
Michael Hersche, Giacomo Camposampiero, Roger Wattenhofer +2
This work compares large language models (LLMs) and neuro-symbolic approaches in solving Raven's progressive matrices (RPM), a visual abstract reasoning test that involves the unde…
On the Role of Noise in Factorizers for Disentangling Distributed Representations
Geethan Karunaratne, Michael Hersche, Abu Sebastian +1
To efficiently factorize high-dimensional distributed representations to the constituent atomic vectors, one can exploit the compute-in-superposition capabilities of vector-symboli…
Limits of Transformer Language Models on Learning to Compose Algorithms
Jonathan Thomm, Giacomo Camposampiero, Aleksandar Terzic +3
We analyze the capabilities of Transformer language models in learning compositional discrete tasks. To this end, we evaluate training LLaMA models and prompting GPT-4 and Gemini o…
MI-BMInet: An Efficient Convolutional Neural Network for Motor Imagery Brain--Machine Interfaces with EEG Channel Selection
Xiaying Wang, Michael Hersche, Michele Magno +1
A brain--machine interface (BMI) based on motor imagery (MI) enables the control of devices using brain signals while the subject imagines performing a movement. It plays a vital r…
Towards Learning Abductive Reasoning using VSA Distributed Representations
Giacomo Camposampiero, Michael Hersche, Aleksandar TerziÄ +3
We introduce the Abductive Rule Learner with Context-awareness (ARLC), a model that solves abstract reasoning tasks based on Learn-VRF. ARLC features a novel and more broadly appli…
Terminating Differentiable Tree Experts
Jonathan Thomm, Michael Hersche, Giacomo Camposampiero +3
We advance the recently proposed neuro-symbolic Differentiable Tree Machine, which learns tree operations using a combination of transformers and Tensor Product Representations. We…