Hacker News
- Deep learning has a size problem https://heartbeat.fritz.ai/deep-learning-has-a-size-problem-ea601304cd8 45 comments
Linking pages
Linked pages
- [1803.03635] The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks https://arxiv.org/abs/1803.03635 32 comments
- Training a single AI model can emit as much carbon as five cars in their lifetimes | MIT Technology Review https://www.technologyreview.com/s/613630/training-a-single-ai-model-can-emit-as-much-carbon-as-five-cars-in-their-lifetimes/ 30 comments
- MLIR Primer: A Compiler Infrastructure for the End of Mooreâs Law â Google Research https://ai.google/research/pubs/pub48035 23 comments
- Medium https://medium.com/m/signin?isDraft=1&operation=login&redirect=https%3A%2F%2Fmedium.com%2F%40jamie_34747%2F79d382edf22b%3Fsource%3D 19 comments
- GitHub - keras-team/keras-tuner: A Hyperparameter Tuning Library for Keras https://github.com/keras-team/keras-tuner 12 comments
- [1506.02626] Learning both Weights and Connections for Efficient Neural Networks https://arxiv.org/abs/1506.02626 6 comments
- [1503.02531] Distilling the Knowledge in a Neural Network https://arxiv.org/abs/1503.02531 5 comments
- Comet ML - Build better models faster https://www.comet.ml/ 4 comments
- MegatronLM: Training Billion+ Parameter Language Models Using GPU Model Parallelism - NVIDIA ADLR https://nv-adlr.github.io/MegatronLM 1 comment
- Building an Image Recognition Model for Mobile using Depthwise Convolutions | by John Olafenwa | Heartbeat https://heartbeat.fritz.ai/building-an-image-recognition-model-for-mobile-using-depthwise-convolutions-643d70e0f7e2 0 comments
- Exploring Massively Multilingual, Massive Neural Machine Translation – Google AI Blog https://ai.googleblog.com/2019/10/exploring-massively-multilingual.html 0 comments
- Creating a 17 KB style transfer model with layer pruning and quantization | by Jameson Toole | Medium https://heartbeat.fritz.ai/creating-a-17kb-style-transfer-model-with-layer-pruning-and-quantization-864d7cc53693 0 comments
- [1602.07360] SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and &ampampampampampampampampampampampampampampampampampampampampampampampampampampampampampampampLT0.5MB model size https://arxiv.org/abs/1602.07360 0 comments
- Launching TensorFlow Lite for Microcontrollers « Pete Warden's blog https://petewarden.com/2019/03/07/launching-tensorflow-lite-for-microcontrollers/ 0 comments
- GitHub - IntelLabs/distiller: Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller https://github.com/NervanaSystems/distiller 0 comments
- The Staggering Cost of Training SOTA AI Models | by Synced | SyncedReview | Medium https://medium.com/syncedreview/the-staggering-cost-of-training-sota-ai-models-e329e80fa82 0 comments
- Analysis of deep neural networks. By Alfredo Canziani, Thomas Molnar… | by Eugenio Culurciello | Medium https://medium.com/@culurciello/analysis-of-deep-neural-networks-dcf398e71aae 0 comments
Related searches:
Search whole site: site:heartbeat.fritz.ai
Search title: Deep learning has a size problem. Shifting from state-of-the-art accuracy… | by Jameson Toole | Heartbeat
See how to search.