MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in SuperpositionNicolas MenetMichael Herscheet al.2023NeurIPS 2023
Heterogeneous Embedded Neural Processing Units Utilizing PCM-based Analog In-Memory ComputingIrem Boybat-KaraThomas Boeschet al.2024IEDM 2024
TCNCA: Temporal Convolution Network with Chunked Attention for Scalable Sequence ProcessingAleksandar TerzicMichael Herscheet al.2023NeurIPS 2023
On the role of noise in factorizers for disentangling distributed representationsKumudu Geethan KarunaratneMichael Herscheet al.2024NeurIPS 2024
Generalized Key-Value Memory to Flexibly Adjust Redundancy in Memory-Augmented NetworksDenis KleykoKumudu Geethan Karunaratneet al.2022IEEE TNNLS
RETRO-LI: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift GeneralizationGentiana RashitiKumudu Geethan Karunaratneet al.2024ECAI 2024
Decoding Superpositions of Bound Symbols Represented by Distributed RepresentationsMichael HerscheZuzanna Opalaet al.2023NeSy 2023
Factorizers for Distributed Sparse Block CodesMichael HerscheAleksandar Terzicet al.2024Neurosymbolic AI
Demonstration of 4-quadrant analog in-memory matrix multiplication in a single modulationManuel Le GalloOscar Hrynkevychet al.2024npj Unconv. Comput.
Exploiting Computation in Superposition via Multiple-Input-Multiple-Output Neural NetworksNicolas MenetMichael Herscheet al.2024NeSy 2024