Overview
This comprehensive course delves into the world of deep learning and artificial neural networks using TensorFlow. Beginning with foundational machine learning concepts, it covers essential topics such as linear classification and regression, before progressing to neurons, model learning, and predictions.
Core modules include:
- Forward propagation
- Activation functions
- Multiclass classification
Practical examples utilizing the MNIST dataset for both image classification and regression tasks provide hands-on experience.
The curriculum also includes instruction on model saving, the usage of Keras, and hyperparameter selection. Advanced sections focus on loss functions and gradient descent optimization techniques, notably Adam.
By the end of this course, participants will be able to:
- Understand fundamental machine learning concepts
- Implement artificial neural network models
- Optimize deep learning models using TensorFlow
This course is perfect for those interested in deep learning, TensorFlow 2, and foundational knowledge for progressing to advanced neural networks such as CNNs, RNNs, LSTMs, and transformers. Proficiency in Python and familiarity with libraries like NumPy and Matplotlib are required.
Provider: Coursera
Syllabus
Taught by
Tags
