SynergicLearning: Neural Network-Based Feature Extraction for Highly-Accurate Hyperdimensional Learning

by   Mahdi Nazemi, et al.

Machine learning models differ in terms of accuracy, computational/memory complexity, training time, and adaptability among other characteristics. For example, neural networks (NNs) are well-known for their high accuracy due to the quality of their automatic feature extraction while brain-inspired hyperdimensional (HD) learning models are famous for their quick training, computational efficiency, and adaptability. This work presents a hybrid, synergic machine learning model that excels at all the said characteristics and is suitable for incremental, on-line learning on a chip. The proposed model comprises an NN and a classifier. The NN acts as a feature extractor and is specifically trained to work well with the classifier that employs the HD computing framework. This work also presents a parameterized hardware implementation of the said feature extraction and classification components while introducing a compiler that maps any arbitrary NN and/or classifier to the aforementioned hardware. The proposed hybrid machine learning model has the same level of accuracy (i.e. ±1 improvement in accuracy compared to HD learning models. Additionally, the end-to-end hardware realization of the hybrid model improves power efficiency by 1.60x compared to state-of-the-art, high-performance HD learning implementations while improving latency by 2.13x. These results have profound implications for the application of such synergic models in challenging cognitive tasks.


page 5

page 6


ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification

Classifiers that can be implemented on chip with minimal computational a...

A Hardware-Friendly Algorithm for Scalable Training and Deployment of Dimensionality Reduction Models on FPGA

With ever-increasing application of machine learning models in various d...

Transferable Cross-Tokamak Disruption Prediction with Deep Hybrid Neural Network Feature Extractor

Predicting disruptions across different tokamaks is a great obstacle to ...

Leveraging Intrinsic Gradient Information for Machine Learning Model Training

Designing models that produce accurate predictions is the fundamental ob...

Learning with Analytical Models

To understand and predict the performance of parallel and distributed pr...

Bioinspired Cortex-based Fast Codebook Generation

A major archetype of artificial intelligence is developing algorithms fa...

Supervised Learning in Automatic Channel Selection for Epileptic Seizure Detection

Detecting seizure using brain neuroactivations recorded by intracranial ...

Please sign up or login with your details

Forgot password? Click here to reset