Program profile · official sources
Convolutional Neural Networks with TensorFlow in Python
365 Data Science's 'Convolutional Neural Networks with TensorFlow in Python' is an advanced-level, online, self-paced course taught by Nikola Pulev and Iskren Vankov. The provider lists a headline duration of four hours and five lesson hours; the curriculum covers image kernels, CNN motivation, feature maps, and pooling layers before applying these concepts to the MNIST dataset using TensorFlow. Students learn to optimize network performance with L2 regularization, dropout, and data augmentation, and track metrics using TensorBoard. A real-world project involves classifying fashion items. Earning the provider-issued course certificate requires course completion and passing the course exam, with general terms specifying a 60 percent or higher passing grade. The provider lists 6 CPE credits; acceptance depends on individual state boards. Intermediate Python and machine-learning knowledge are required; NumPy and neural-network fundamentals are recommended.
Facts checked 30 Sep 2026
- Price
- See pricing
Price observation recorded 30 Sep 2026 (not a current price): As shown in the United States on 30 September 2026, the 365 pricing page Self-study card displays $36/month reference price and a promotional $12.50/month equivalent billed annually; the same pricing page FAQ separately states $29/month full access. USD is explicit in the saved pricing page state. These are platform access quotes, not a course-completion total. Certificates are included with Self-study.
- Time
- 4 hours (provider headline; module and exam timings listed separately)
- Level
- Advanced
- Credential
- Provider-issued course certificate
Verifiable credential with Credential ID and Credential Link; sharable on LinkedIn/resumes; downloadable upon passing. Certificates are included with the Self-study learning plan.
- Format
- 100% online, self-paced course
- Prerequisites
- Python (version 3.8 or later), TensorFlow 2 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: Deep Learning with TensorFlow 2, Machine Learning in Python, Math Foundation for ML.
Commercial status: no commercial relationship is documented for this page. The verification link goes directly to the official provider source.
Sources ↗
No accepted numeric price in this registry. See the sourced pricing details below.
See the full registry price landscape. Prices retain their stated payment scope; they are not comparable completion costs.
What’s covered
- Introduction to the course
- Kernels
- CNN Introduction
- Neural network techniques (revision)
- Setting up the environment
- CNN assembling - MNIST
- Tensorboard: Visualization tool for TensorFlow
- Common techniques for better performance of neural networks
- A practical project: Labelling fashion items
- Understanding CNNs
- Popular CNN architectures
- Course exam
Prerequisites: Python (version 3.8 or later), TensorFlow 2 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: Deep Learning with TensorFlow 2, Machine Learning in Python, Math Foundation for ML.
What you actually do
- Introduction to the course : 10 min; Section 1 · Source
- Kernels : 17 min; Section 2 · Source
- CNN Introduction : 23 min; Section 3 · Source
- Neural network techniques (revision) : 9 min; Section 4 · Source
- Setting up the environment : 3 min; Section 5 · Source
- CNN assembling - MNIST : 46 min; Section 6 · Source
- Tensorboard: Visualization tool for TensorFlow : 38 min; Section 7 · Source
- Common techniques for better performance of neural networks : 19 min; Section 8 · Source
- A practical project: Labelling fashion items : 82 min; Section 9 · Source
- Understanding CNNs : 7 min; Section 10 · Source
- Popular CNN architectures : 19 min; Section 11 · Source
- Course exam : 30 min; Section 12 · Source
What the credential is
- Credential type
- Provider-issued course certificate · 365datascience.com / convolutional-neural-networks-with-tensorflow-in-python
- Credential
- Course Certificate · 365datascience.com / certificates
- Issuer
- 365 Data Science · 365datascience.com / certificates
- Sharing
- Verifiable credential with Credential ID and Credential Link; sharable on LinkedIn/resumes; downloadable upon passing. Certificates are included with the Self-study learning plan. · 365datascience.com / certificates
- Exam requirement
- Complete the course and pass its course exam with 60% or above under the general certificate terms. Certificates are included with the Self-study learning plan. · 365datascience.com / certificates
Who should skip it
Alternatives in the registry
Related by topic or level.
- Deep Learning with TensorFlow 2 : Check official price; 5 hours (provider headline; module and exam timings listed separately).
- Deep Learning with Pytorch : Check official price; 2 hours (provider headline; module and exam timings listed separately).
- Introduction to Hugging Face : Check official price; 2 hours (provider headline; module and exam timings listed separately).
Change log
- : Initial recorded review of official program details. · Source