Michael A. Casey

Sean Paulsen, Michael Casey

We present a sequential transfer learning framework for transformers on functional Magnetic Resonance Imaging (fMRI) data and demonstrate its significant benefits for decoding musical timbre. In the first of two phases, we pre-train our stacked-encoder transformer architecture on Next Thought Prediction, a self-supervised task of predicting whether or not one sequence of fMRI data follows another. This phase imparts a general understanding of the temporal and spatial dynamics of neural activity, and can be applied to any fMRI dataset. In the second phase, we fine-tune the pre-trained models and train additional fresh models on the supervised task of predicting whether or not two sequences of fMRI data were recorded while listening to the same musical timbre. The fine-tuned models achieve significantly higher accuracy with shorter training times than the fresh models, demonstrating the efficacy of our framework for facilitating transfer learning on fMRI data. Additionally, our fine-tuning task achieves a level of classification granularity beyond standard methods. This work contributes to the growing literature on transformer architectures for sequential transfer learning on fMRI data, and provides evidence that our framework is an improvement over current methods for decoding timbre.

Sean Paulsen, Michael Casey

In this work we introduce a self-supervised pretraining framework for transformers on functional Magnetic Resonance Imaging (fMRI) data. First, we pretrain our architecture on two self-supervised tasks simultaneously to teach the model a general understanding of the temporal and spatial dynamics of human auditory cortex during music listening. Our pretraining results are the first to suggest a synergistic effect of multitask training on fMRI data. Second, we finetune the pretrained models and train additional fresh models on a supervised fMRI classification task. We observe significantly improved accuracy on held-out runs with the finetuned models, which demonstrates the ability of our pretraining tasks to facilitate transfer learning. This work contributes to the growing body of literature on transformer architectures for pretraining and transfer learning with fMRI data, and serves as a proof of concept for our pretraining tasks and multitask pretraining on fMRI data.

Andy M. Sarroff, Victor Shepardson, Michael A. Casey

Complex-valued neural networks (CVNNs) are an emerging field of research in neural networks due to their potential representational properties for audio, image, and physiological signals. It is common in signal processing to transform sequences of real values to the complex domain via a set of complex basis functions, such as the Fourier transform. We show how CVNNs can be used to learn complex representations of real valued time-series data. We present methods and results using a framework that can compose holomorphic and non-holomorphic functions in a multi-layer network using a theoretical result called the Wirtinger derivative. We test our methods on a representation learning task for real-valued signals, recurrent complex-valued networks and their real-valued counterparts. Our results show that recurrent complex-valued networks can perform as well as their real-valued counterparts while learning filters that are representative of the domain of the data.