Deep Learning Specialization
Issued by
Coursera
The Deep Learning Specialization will help you understand the foundational concepts in deep learning. Build and train Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, and Transformers, and learn how to make them better with Dropout, BatchNorm, Xavier/He initialization, and more. Learn industry applications using Python and TensorFlow to tackle real-world use cases such as speech recognition, music synthesis, chatbots, machine translation, natural language processing, and more.
Additional DetailsSkills
- Artificial Neural Network
- Attention Models
- Backpropagation
- Convolutional Neural Network
- Deep Learning
- Facial Recognition Systems
- Gated Recurrent Unit (GRU)
- Hyperparameter Tuning
- Inductive Transfer
- Long Short-Term Memory (LSTM)
- Machine Learning
- Mathematical Optimization
- Multi-Task Learning
- Natural Language Processing
- Neural Network Architecture
- Object Detection and Segmentation
- Optimization
- Python Programming
- Recurrent Neural Network
- TensorFlow
- Transfer Learning
- Transformers
Earning Criteria
Endorsements
-
American Council on Education
This credential has been successfully evaluated by the American Council on Education for college credit. It is recommended for a total of 10 college credits. For more information about ACE Learning Evaluations, visit www.acenet.edu. -
American Council on Education
2 semester hours in Neural Networks and Deep Learning in the lower-division undergraduate category -
American Council on Education
2 semester hours in Improving Deep Neural Networks in the lower-division undergraduate category -
American Council on Education
1 semester hour in Structuring Machine Learning Projects in the lower-division undergraduate category -
American Council on Education
2 semester hours in Convolutional Neural Networks in the lower-division undergraduate category -
American Council on Education
3 semester hours in Sequence Models in the lower-division undergraduate category