Skip to content
#

mini-batch-training

Star

Here are 3 public repositories matching this topic...

Mubarraqqq / gnn-challenge

Star 3

This project focuses on predicting maternal-fetal health outcomes, specifically early detection of preeclampsia, by learning transferable representations from cfRNA and placental transcriptomic data.

machine-learning bioinformatics deep-learning graph computational-biology representation-learning transcriptomics graphsage graph-neural-networks inductive-learning gnn maternal-health transcriptomics-data heterogeneous-graphs torch-geometric preeclampsia mini-batch-training
  • Updated Apr 15, 2026
  • Python

carysva / Tuning-Deep-Neural-Networks-on-E-Commerce-Data

Star 0

Experimented with 16+ deep neural network configurations in TensorFlow on e-commerce demand data to compare tuning sensitivity, performance, and runtime tradeoffs. Best model: 2-layer (128->64), ReLU, Adam, LR 0.001, batch 128, early stopping, validation MAE 12.54 in ~126 seconds.

python machine-learning deep-neural-networks deep-learning tensorflow feature-engineering mini-batch-training pipeline-engineering
  • Updated Apr 29, 2026
  • Python

carysva / Neural-Network-Deep-Learning

Star 0

Feed-forward neural network trained incrementally on large-scale e-commerce pricing data to predict order quantity demand. Designed for datasets too large to fit into memory, the system processes data in chunks, engineers features on the fly, and updates the model via mini-batch learning - mirroring real-world production ML pipelines.

python deep-learning tensorflow numpy keras pandas matplotlib chunked-uploads permutation-importance partial-dependence-plots mini-batch-training
  • Updated Mar 20, 2026
  • Python

Improve this page

Add a description, image, and links to the mini-batch-training topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the mini-batch-training topic, visit your repo's landing page and select "manage topics."

Learn more