InData Science CollectivebyErfan Eshratifar·Oct 20You Don’t Need JevCheap LLM labels, 220 hand-labeled examples, and a 150M-parameter model on a CPU can match or beat a hosted decision model at a fraction of…A response icon12A response icon12
Erfan Eshratifar·Jul 24, 2022Variational Auto Encoder (VAE) for the Numerai DatasetThe Numerai dataset contains decades of historical data on the global stock market. Machine learning models trained on the dataset learn to…
Erfan Eshratifar·Dec 19, 2021How to build a deep learning GPU workstation while saving $1500?Companies like Lambda, Bizon, Digital Storm offer pre-built deep learning GPU rigs that are often more expensive than building the rig from…
InTDS ArchivebyErfan Eshratifar·Mar 4, 2020Cloud vs On-device AI? Maybe something in between!Put your AI on the cloud only when you need to put it on the cloud.A response icon2A response icon2
InTDS ArchivebyErfan Eshratifar·Dec 9, 2019Defining User Restrictions for GPUsWe are using Lambda Lab’s 4-GPU workstations at the University of Southern California. As multiple users can be simultaneously running…A response icon4A response icon4
InTDS ArchivebyErfan Eshratifar·Sep 17, 2019BottleNet: Learnable Feature Compression for Accelerated Edge IntelligenceUpload only 316 bytes of data to the cloud for ImageNet classification