Research Partners
 | IMEC |
Sources of Funding
| Edge Companions |  |
| Cerberus |  |
| SwissChips |  |
| ACCESS |  |
We use I2-CE (Iso-Indexed Code-booked Ensembles) as a means for fast, efficient, and robust inference at the edge.
Ensemble learning improves generalizationby combining the outputs of multiple learners, but its computational and memory requirements grow linearly with the number of learners. We address this challenge by enforcing a single, shared index map across all learners, distinguishing their behaviors solely through compact, learner-specific codebooks.
Codebook-based methodologies restrict the admissible values of weights of trained models to a discrete set, which can be stored in lookup tables and indexed by low-bitwidth pointers. By storing only one set of indices, shared between learners, we dramatically reduce memory requirements since the memory overhead for additional learners is limited to that of a (small) codebook.
Moreover, such a structure produces a set of highly regular models that greatly benefit from parallel execution. Leveraging this, our framework exploits data-level parallelism within and across learners, employing Single Instruction Multiple Data (SIMD) instructions for run-time optimization. |
I2-CE execution: each iso-index is unpacked and used to read a weight from each learner codebook, which is then multiplied by the input.Related Publications
