TensorFlow in Practice Specialization
E824069
TensorFlow in Practice Specialization is an online deep learning program on Coursera that teaches practical TensorFlow skills for building and deploying neural network models.
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
Coursera specialization
ⓘ
deep learning program ⓘ online course specialization ⓘ |
| certificate | shareable certificate upon completion ⓘ |
| focusesOn |
TensorFlow
NERFINISHED
ⓘ
deep learning ⓘ neural networks ⓘ |
| hasAssessment |
programming assignments
ⓘ
quizzes ⓘ |
| hasFormat | online ⓘ |
| hasPart |
Convolutional Neural Networks in TensorFlow
NERFINISHED
ⓘ
Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning NERFINISHED ⓘ Natural Language Processing in TensorFlow NERFINISHED ⓘ Sequences, Time Series and Prediction NERFINISHED ⓘ |
| includes |
hands-on programming assignments
ⓘ
practical projects ⓘ |
| language | English ⓘ |
| learningOutcome |
ability to build TensorFlow models
ⓘ
ability to deploy trained models ⓘ ability to train deep neural networks ⓘ |
| level | intermediate ⓘ |
| offeredAs | subscription program on Coursera ⓘ |
| platform | Coursera NERFINISHED ⓘ |
| provider | Coursera NERFINISHED ⓘ |
| subjectArea |
artificial intelligence
ⓘ
computer science ⓘ machine learning ⓘ |
| targetAudience |
data scientists
ⓘ
machine learning practitioners ⓘ software developers ⓘ |
| teachesConcept |
TensorFlow data pipelines
NERFINISHED
ⓘ
callbacks and checkpoints in TensorFlow ⓘ convolutional neural networks ⓘ image classification with CNNs ⓘ model overfitting and regularization ⓘ natural language processing with neural networks ⓘ recurrent neural networks ⓘ sequence models ⓘ time series forecasting ⓘ training and validation splits ⓘ |
| teachesSkill |
building neural network models
ⓘ
deploying neural network models ⓘ model deployment ⓘ model evaluation with TensorFlow ⓘ model training with TensorFlow ⓘ practical TensorFlow programming ⓘ |
| usesSoftware | TensorFlow NERFINISHED ⓘ |
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.