Imperial College London > Talks@ee.imperial > CAS Talks > Enabling Binary Neural Network Training on the Edge
Log inImperial users Other users No account?Information onFinding a talk Adding a talk Syndicating talks Who we are Everything else |
Enabling Binary Neural Network Training on the EdgeAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact George A Constantinides. The ever-growing computational demands of increasingly complex machine learning models frequently necessitate the use of powerful cloud-based infrastructure for their training. Binary neural networks are known to be promising candidates for on-device inference due to their extreme compute and memory savings over higher-precision alternatives. In this work, we demonstrate that they are also strongly robust to gradient quantization, thereby making the training of modern models on the edge a practical reality. We introduce a low-cost binary neural network training strategy exhibiting sizable memory footprint reductions and energy savings vs Courbariaux & Bengio’s standard approach. Against the latter, we see coincident memory requirement and energy consumption drops of 2—6x, while reaching similar test accuracy in comparable time, across a range of small-scale models trained to classify popular datasets. We also showcase ImageNet training of ResNetE-18, achieving a 3.12x memory reduction over the aforementioned standard. Such savings will allow for unnecessary cloud offloading to be avoided, reducing latency, increasing energy efficiency and safeguarding privacy. This talk is part of the CAS Talks series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsType the title of a new list here HiPEDS Seminar Series IEEE TalksOther talks |