Zahra-Bakhtiari

Building-Deep-Neural-Network-Step-by-Step-Instruction

building a deep neural network with as many layers as you want!

Graph_Machine_Learning

Graph_Neural_Network_for_biological_predictions

RotatE to Biological Predictions:

Improving_Deep_Neural_Networks_via_Hyperparameter_Tuning

biokg_bug_fix

Covid19-QA-NLP

Deep-Neural-Network-for-Image-Classification

Building a cat classifier via L-layer neural network

Logistic-Regression-with-a-Neural-Network-mindset

Building a logistic regression classifier to recognize cats

Microsoft-Vision-Classifier

Numpy_Tutorial

Predictive-Wavelength-Switching

PyTorch_Tutorial

Rotational-Embedding-Space-for-Graph-Neural-Networks

Designing the right embedding space for a neural network has tremendous implications for model expressivity, flexibility, and accuracy. This is especially true of knowledge graphs, which contain various type of relationships but are notoriously incomplete. In this post, we provide a gentle introduction to knowledge graphs and explain how one clever GNN model achieved state-of-the-art results by approaching the embedding space in a novel way.

Summarization-of-financial-reports-with-GPT3

TensorFlow_Introduction