Building and Optimizing AI Models

This course is part of Transformers Unleashed: Master the Architecture of Modern AI Professional Certificate

Instructor: Professionals from the Industry

Access provided by Anima Educacao

8 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

7 hours to complete

Flexible schedule

Learn at your own pace

8 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

7 hours to complete

Flexible schedule

Learn at your own pace

What you'll learn

Train and evaluate predictive machine learning models using supervised and unsupervised algorithms
Design custom neural network architectures for AI applications
Optimize deep learning models using transfer learning and performance tuning
Benchmark AI algorithms to evaluate efficiency, accuracy, and computational cost

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

20 assignments¹

AI Graded see disclaimer

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your Machine Learning expertise

This course is part of the Transformers Unleashed: Master the Architecture of Modern AI Professional Certificate

When you enroll in this course, you'll also be enrolled in this Professional Certificate.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate from Coursera

There are 8 modules in this course

Building and Optimizing AI Models introduces the foundational engineering practices required to design, train, and optimize machine learning models for modern AI systems. In this course, you will explore statistical machine learning methods, neural network architectures, and deep learning optimization techniques used to develop high-performing predictive models.

You will begin by applying supervised and unsupervised algorithms to train and evaluate predictive models. Next, you will design custom neural network architectures and experiment with different layer configurations to improve model accuracy and efficiency. The course also introduces transfer learning and deep learning optimization strategies that help adapt pretrained models to domain-specific tasks. Finally, you will analyze algorithm performance and benchmark model implementations to understand trade-offs between accuracy, latency, and computational cost. By the end of this course, you will be able to design neural networks, optimize deep learning workflows, and evaluate model performance using industry-standard metrics. Tools and technologies covered include Python, TensorFlow, neural network frameworks, and model performance benchmarking techniques.

You will apply supervised and unsupervised algorithms to train predictive models using structured datasets. You will implement cross-validation techniques to validate model reliability and interpret results to ensure robust performance.

What's included

3 videos1 reading2 assignments

3 videos Total 17 minutes

Welcome and What You’ll Learn 4 minutes
Supervised vs. Unsupervised Modeling: When to Use Each 5 minutes
Walkthrough: Training Logistic Regression and K-Means in scikit-learn 8 minutes

1 reading Total 10 minutes

How Cross-Validation Improves Model Reliability 10 minutes

2 assignments Total 22 minutes

Hands-On Activity: Train Two Models and Run 5-Fold CV 15 minutes
Practice Quiz: Model Fit Check 7 minutes

You will evaluate model performance using accuracy and F1 metrics, identify weaknesses, and refine features systematically. You will iterate on feature engineering decisions to meet defined performance targets

What's included

3 videos1 reading3 assignments

3 videos Total 15 minutes

Why Metrics Drive Better Modeling 4 minutes
Interpreting Accuracy, Precision, Recall, and F1 7 minutes
Demo: Interaction Features Improve F1 4 minutes

1 reading Total 10 minutes

Feature Engineering Fundamentals: Transform, Combine, Improve 10 minutes

3 assignments Total 42 minutes

Hands-On Activity: Improve a Model’s F1 Score with New Features 15 minutes
Practice Quiz: Fix the Model 7 minutes
Graded Quiz: Build, Validate, and Improve a Predictive Model 20 minutes

You will analyze candidate neural network topologies such as CNNs, RNNs, and Transformers. You will evaluate task requirements, data characteristics, and compute constraints to select the most appropriate architecture.

What's included

3 videos1 reading2 assignments

3 videos Total 8 minutes

Welcome and Why Architecture Choices Matter 2 minutes
Comparing Neural Network Topologies 3 minutes
How to Evaluate Architecture Fit in Practice 3 minutes

1 reading Total 10 minutes

Understanding Task, Data, and Compute Constraints 10 minutes

2 assignments Total 22 minutes

Hands-on Activity: Choose the Best Architecture Under Real Constraints 15 minutes
Practice Quiz: Architecture Selection Mini-Review 7 minutes

You will create custom neural-network architectures by composing layers, activations, and regularization techniques. You will test architectural decisions to improve generalization and training stability.

What's included

3 videos1 reading3 assignments

3 videos Total 9 minutes

Why Build Custom Architectures 2 minutes
Layers, Activations, and Regularization 2 minutes
Screencast: Constructing a Custom Model in PyTorch 5 minutes

1 reading Total 10 minutes

Designing a Custom Network Step by Step 10 minutes

3 assignments Total 42 minutes

Hands-on Activity: Build Your Own Network Architecture 15 minutes
Practice Quiz: Improve a Baseline Model With Regularization 7 minutes
Graded Assessment: Custom Neural Network Architechture Evaluation 20 minutes

You will apply transfer-learning workflows to fine-tune pretrained models on domain-specific datasets. You will experiment with freezing and unfreezing layers to improve model adaptation.

What's included

2 videos1 reading2 assignments

You will evaluate deep model configurations by comparing accuracy, latency, and memory usage. You will balance performance and efficiency to determine the most suitable production-ready configuration.

What's included

3 videos1 reading3 assignments

3 videos Total 17 minutes

Accuracy vs. Efficiency: The Real Trade-Offs 6 minutes
Hyperparameter Sweeps: Comparing Configurations Fairly (Optuna Example) 5 minutes
Quantization as a Configuration Choice: Speed vs. Accuracy (TensorRT Example) 6 minutes

1 reading Total 10 minutes

Practical Model Training Tips for Reliable Machine Learning Performance 10 minutes

3 assignments Total 40 minutes

Hands-On Activity: Run a Mini Optimization Comparison 15 minutes
Practice Quiz: Evaluating Model Performance Trade-Offs 5 minutes
Graded Assessment: Model Optimization Decision Challenge 20 minutes

You will analyze the computational complexity of algorithms and evaluate how data structures affect performance. You will select optimal approaches based on scalability and workload demands.

What's included

3 videos1 reading2 assignments

3 videos Total 15 minutes

Welcome and Why Speed Matters in Real AI Systems 4 minutes
Understanding Complexity: From Big-O to Practical Speed 5 minutes
Hidden Costs: Constants, Cache Effects, and Real-World Slowdowns 6 minutes

1 reading Total 10 minutes

Data Structures That Scale: Trees, Hash Maps, and Heaps 10 minutes

2 assignments Total 20 minutes

Hands-On Activity: Complexity Match-Up: Predict the Faster Method 10 minutes
Practice Quiz: Test Your Complexity and Data Structure Skills 10 minutes

You will create prototype algorithms and design structured benchmarks to measure latency, throughput, and memory usage. You will interpret benchmark results to evaluate performance trade-offs and justify implementation decisions.