Saquib Rahman K.
After 365:
Data Scientist | EXL
See all reviews
Online Course
Deep Learning with Pytorch
with
Gaurav Sarkar
Create State of the Art Neural Networks for Deep Learning with Meta's PyTorch Deep Learning Library!
835 students already enrolled
Skill level:
Advanced
Duration:
2 hours
-
Lessons (2 hours)
- Lessons (2 hours)
CPE credits:
2.5
CPE stands for Continuing Professional Education and represents the mandatory credits a wide range of
professionals must earn to maintain their licenses and stay current with regulations and best
practices. One CPE credit typically equals 50 minutes of learning. For more details, visit NASBA's
official website: www.nasbaregistry.org
CPE stands for Continuing Professional Education and represents the mandatory credits a wide range of
professionals must earn to maintain their licenses and stay current with regulations and best
practices. One CPE credit typically equals 50 minutes of learning. For more details, visit NASBA's
official website: www.nasbaregistry.org
Accredited
certificate
What you learn
- Build your first neural network using PyTorch.
- Perform regression tasks with PyTorch models.
- Implement classification models in PyTorch.
- Evaluate model performance effectively.
- Learn how to use Kaggle for projects.
Topics & tools
Deep LearningPytorchNeural NetworksPythonKaggleMachine and Deep Learning
Your instructor
AI Solution Engineer at Intel | Hugging Face Fellow | Kaggle Expert
Track record
Bringing real-world expertise from leading global companies
Academic background
Master's degree, Computer Science
Course OVERVIEW
Description
CPE Credits: 2.5
Field of Study: Information Technology
Delivery Method: QAS Self Study
Delivery Method: QAS Self Study
Ready to master deep learning with PyTorch? This course takes you from foundational concepts to hands-on neural network deployment, designed to provide you with practical skills and real-world experience.
Dive into the world of tensors, understand dimensions, notation, and tensor construction. Seamlessly integrate PyTorch with NumPy and leverage common PyTorch functions. Master GPU acceleration to dramatically enhance computational performance. Explore automatic differentiation and PyTorch’s powerful autograd system. Build efficient data pipelines and construct your first neural networks. Implement essential components like loss functions, training loops, and evaluation metrics with hands-on coding exercises.
Tackle real-world regression and classification problems. Learn debugging techniques and best practices for developing reliable models.
Get introduced to Kaggle, the global playground for data science. Step-by-step guidance to participate effectively in regression and classification competitions.
Solidify your skills and prepare to confidently apply deep learning to practical challenges.
Prerequisites
- Python (version 3.8 or later), PyTorch library, and a code editor or IDE (e.g., Jupyter Notebook, VS Code, or Google Colab)
- Intermediate Python and machine learning knowledge is required.
- Familiarity with NumPy and neural network fundamentals is recommended.
Advanced preparation
Curriculum
41 lessons
18 exercises
1 exam
- 2. 🧠Learning Approach3 min3 minDeep Learning as a Concept FreeExercise Free
- 3. 🔥Learning PyTorch88 min88 minPyTorch: World of Tensors FreeTensor Dimensions and NotationExerciseHow Tensors Are ConstructedPyTorch and NumPy work well togetherExerciseMasking OperationCommon PyTorch functionsExerciseCoding Exercise 1: Tensor Transformations and OperationsCoding Exercise 1: SolutionExerciseDevice Management: CPU or GPUCoding Exercise 2: Unleashing GPU Power with PyTorchCoding Exercise 2: SolutionExerciseAutomatic Differentiation: Learning MechanismCoding Exercise 3: The Magic of Autograd in PyTorchCoding Exercise 3: SolutionExerciseDataset: How to Feed Data to ModelCoding Exercise 4: Building Efficient Data Pipelines with PyTorchCoding Exercise 4: SolutionExerciseBuilding a Neural Network with PyTorchCoding Exercise 5: Building Your First Neural Network in PyTorchCoding Exercise 5: SolutionExerciseLoss Function: How Good/ Bad is your performanceCoding Exercise 6: Choosing and Using Loss Functions in PyTorchCoding Exercise 6: SolutionExerciseTraining Loop: Putting it all togetherCoding Exercise 7: Implementing a Simple Training LoopCoding Exercise 7: SolutionExerciseModel Evaluation: Final Performance ReportCoding Exercise 8: Applying and Interpreting Evaluation MetricsCoding Exercise 8: SolutionExercise
- 4. 🛠️Hands-On Session10 min10 minRegression ProblemClassification ProblemDebugging and Best Practices
- 5. 🏆Kaggle Competition10 min10 minIntroduction to Kaggle — Your Playground for Data ScienceHands-On Kaggle Regression Based Competition (Step-by-Step)Hands-On Kaggle Classification Based Competition (Step-by-Step)🎓 Concluding Lesson
- 6. Course exam60 min60 minCourse exam
Free lessons
1.1 Meet your instructor
1 min
1.2 Why PyTorch for Deep Learning
2 min
1.3 Learning Objectives
2 min
1.4 PyTorch vs. TensorFlow
4 min
2.1 Deep Learning as a Concept
3 min
3.1 PyTorch: World of Tensors
3 min
#1 most reviewed
AI and data learning platform on Trustpilot.
96%
of our students recommend
365 Data Science.
9 in 10
of our graduates landed a new AI & data job
after enrollment
ACCREDITED certificates
Craft a resume and LinkedIn profile you’re proud of—featuring certificates recognized by leading global
institutions.
Earn CPE-accredited credentials that showcase your dedication, growth, and essential skills—the qualities
employers value most.
Certificates are included with the Self-study learning plan.
How it WORKS
Student REVIEWS
