Search Results for author:
Found 3 papers, 0 papers with code
Limits of Transformer Language Models on Learning to Compose Algorithms
We analyze the capabilities of Transformer language models in learning compositional discrete tasks.
TCNCA: Temporal Convolution Network with Chunked Attention for Scalable Sequence Processing
We build upon their approach by replacing the linear recurrence with a special temporal convolutional network which permits larger receptive field size with shallower networks, and reduces the computational complexity to $O(L)$.
Factorizers for Distributed Sparse Block Codes
Secondly, the proposed factorizer maintains a high accuracy when queried by noisy product vectors generated using deep convolutional neural networks (CNNs).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
