- Activités du site
- Anton
- Build and train neural network models using TensorFlow 2.x
- Build and train models for binary classification
- Build and train models for multi-class categorization
- Build sequential models with multiple layers
- Build, compile and train machine learning (ML) models
- Identify strategies to prevent overfitting, including augmentation and dropout
- Plot loss and accuracy of a trained model
- Preprocess data to get it ready for use in a model
- Use callbacks to trigger the end of training cycles
- Use datasets from different sources
- Use datasets from tf.data.datasets
- Use datasets in different formats, including json and csv
- Use models to predict results
- Use pretrained models (transfer learning)
- Use TensorFlow 2.x
- Ensure that inputs to a model are in the correct shape
- Ensure that you can match test data to the input shape of a neural network
- Ensure you can match output data of a neural network to specified input shape for test data
- Extract features from pre-trained models
- Understand batch loading of data
- Canon – Session #1
- Classification d’iris – #1
- Classification d’iris – #2
- Classification d’iris – #3
- Classification d’iris – #4
- DWQA Ask Question
- DWQA Questions
- Formation au Deep Learning et à TensorFlow
- Image classification
- Introduction
- Introduction à l’Intelligence Artificielle
- Membres
- Natural language processing (NLP)
- Page d’exemple
- Politique de confidentialité
- RNN, LSTM pour Time Series
- sitemap
- Test
- Time series, sequences and predictions
- Prepare data for time series learning
- Adjust the learning rate dynamically in time series, sequence and prediction models
- Identify and compensate for sequence bias
- Prepare features and labels
- Train, tune and use time series, sequence and prediction models
- Understand MAE and how it can be used to evaluate accuracy of sequence models
- Use RNNs and CNNs for time series, sequence and forecasting models
- Use TensorFlow for forecasting
- Identify when to use trailing versus centred windows