-
-
- Transfer Credit
- Online Learning
- Events
- Custom Programs
-
-
-
- Academic Services
- Course and Program Information
- Student Aid
-
-
-
Berkeley Global
This is a foundational Artificial Intelligence course to help you understand the deep learning frameworks that build upon the underpinning neural network architecture. Artificial Intelligence is pervasive across all domains and can be used for meaningful applications in multiple fields, including cancer detection using MRI scans, autonomous vehicles, speech recognition, weather forecasting and more. You will gain an understanding of versatile AI algorithms such as CNN, RNN, and implement them using frameworks such as keras, pytorch and more.
Prerequisites:
- Prior knowledge of programming, Python preferred
- Knowledge of statistics as covered in an undergraduate level course
- Experience working with machine learning algorithms
Learner Outcomes
Upon completion of this course, students will be able to:
- Define the field of Artificial Intelligence (AI) and its core principles.
- Explain the basics of neural networks and their historical development.
- Differentiate between traditional machine learning and deep learning approaches.
- Understand the architecture and components of neural networks.
- Explore optimization techniques, including gradient descent, regularization, and hyperparameter tuning.
- Implement basic neural network models for supervised learning tasks.
- Comprehend and apply Convolutional Neural Networks (CNNs) for image data analysis.
- Implement Recurrent Neural Networks (RNNs) for sequential data processing.
- Develop autoencoders for unsupervised learning tasks.
- Differentiate between various types of reinforcement learning algorithms.
- Implement reinforcement learning techniques for solving control and decision-making problems.
- Evaluate the strengths and weaknesses of reinforcement learning approaches.
- Implement AI algorithms for real-world applications, such as image classification, speech recognition, and Natural Language Processing (NLP).
- Explore the use of AI in recommender systems, autonomous vehicles, and weather forecasting.
- Analyze the ethical and societal implications of AI applications.
- Investigate emerging AI techniques, including advanced Transformer models.
- Explore AI generative algorithms, such as Generative Adversarial Networks (GANs) and ChatGPT.
- Assess the potential impact of AI advancements on various industries and domains.
Loading...
Sections
Spring 2025 enrollment opens on October 21!