- Why Are Eight Bits Enough for Deep Neural Networks? http://petewarden.com/2015/05/23/why-are-eight-bits-enough-for-deep-neural-networks/ 45 comments
- Hardware for Deep Learning. Part 3: GPU | by Grigory Sapunov | Intento https://blog.inten.to/hardware-for-deep-learning-part-3-gpu-8906c1644664 13 comments
- How to Fit Large Neural Networks on the Edge | by Bharath Raj | Heartbeat https://heartbeat.fritz.ai/how-to-fit-large-neural-networks-on-the-edge-eb621cdbb33 0 comments
- 8-Bit Quantization and TensorFlow Lite: Speeding up mobile inference with low precision | by Manas Sahni | Heartbeat https://heartbeat.fritz.ai/8-bit-quantization-and-tensorflow-lite-speeding-up-mobile-inference-with-low-precision-a882dfcafbbd 0 comments
- How TensorFlow Lite Optimizes Neural Networks for Mobile Machine Learning | by Airen Surzyn | Heartbeat https://heartbeat.fritz.ai/how-tensorflow-lite-optimizes-neural-networks-for-mobile-machine-learning-e6ffa7f8ee12 0 comments
Search whole site: site:petewarden.com
Search title: Why are Eight Bits Enough for Deep Neural Networks? « Pete Warden's blog
See how to search.