Explain why the network achieves 100% accuracy on the test set, even though its overall accuracy during training was approximately 94%.
Saturday, 05 August 2023
by EITCA Academy
The achievement of 100% accuracy on the test set, despite an overall accuracy of approximately 94% during training, can be attributed to several factors. These factors include the nature of the test set, the complexity of the network, and the presence of overfitting. Firstly, the test set may differ in various aspects from the training
- Published in Artificial Intelligence, EITC/AI/TFF TensorFlow Fundamentals, TensorFlow in Google Colaboratory, Building a deep neural network with TensorFlow in Colab, Examination review
Tagged under:
Artificial Intelligence, Deep Learning, Neural Networks, Overfitting, Test Set, Training Accuracy
How is the training data split into training and test sets in TensorFlow.js?
Saturday, 05 August 2023
by EITCA Academy
In TensorFlow.js, the process of splitting the training data into training and test sets is a crucial step in building a neural network for classification tasks. This division allows us to evaluate the performance of the model on unseen data and assess its generalization capabilities. In this answer, we will delve into the details of
- Published in Artificial Intelligence, EITC/AI/TFF TensorFlow Fundamentals, TensorFlow.js, Building a neural network to perform classification, Examination review
Tagged under:
Artificial Intelligence, Random Split, Stratified Split, TensorFlow.js, Test Set, Training Data