Convolutional Neural Networks (CNN) Courses and Certifications

Packt

Building and Training Neural Networks with PyTorch

15 ratings at Coursera

Build and train neural networks in PyTorch: image and audio CNNs, YOLO object detection, neural style transfer, transfer learning, and RNN/LSTM sequence models.

• Coursera
• 7 weeks, 1 hour a week
• Self-Paced
• Paid Course

Whizlabs

NVIDIA: Fundamentals of Deep Learning

14 ratings at Coursera

Learn deep learning fundamentals: gradient descent, Perceptron training, forward and backward propagation, activation functions, multi-class classification on MNIST, CNNs, and transfer learning with pre-trained models.

• Coursera
• 2 weeks, 2 hours a week
• Self-Paced
• Paid Course

Coursera

Classify Radio Signals with PyTorch

13 ratings at Coursera

Fine-tune a pretrained CNN in PyTorch to classify radio signal spectrogram images into Squiggle, Noise and Narrowband classes, applying spectrogram augmentation and writing train/eval loops.

• Coursera
• 1 hour 45 minutes
• Self-Paced
• Paid Course

Packt Career Certificate

AI Engineer Professional

7 ratings at Coursera

Build advanced AI systems: tune hyperparameters with cross-validation, design CNNs and RNNs, apply transformers and transfer learning, and deploy models with Docker and Kubernetes.

• Coursera
• 4 weeks, 10 hours a week
• Self-Paced
• Paid Course
• 3 courses

Packt Career Certificate

Deep Learning with Real-World Projects

7 ratings at Coursera

Build, train, and deploy neural networks with TensorFlow and Keras, moving from perceptrons and backpropagation to CNNs, recurrent networks, and transfer learning for medical and natural image projects.

• Coursera
• 4 weeks, 10 hours a week
• Self-Paced
• Paid Course
• 3 courses

Packt Career Certificate

Deep Learning with TensorFlow

6 ratings at Coursera

Build deep learning models in TensorFlow and Keras: artificial neural networks, RNNs, GRUs and LSTMs, and CNNs applied to MNIST, CIFAR-10, time series and image classification.

• Coursera
• 4 weeks, 10 hours a week
• Self-Paced
• Paid Course
• 3 courses

Generative AI: Foundations and Concepts

Learn the mathematics behind generative AI: perceptrons and network architectures, Adam and quasi-Newton optimization, dropout and batch normalization, CNNs, and maximum likelihood with KL divergence.

• Coursera
• 4 weeks, 5 hours a week
• Self-Paced
• Paid Course

Deep Learning for AI Part 1

Build deep learning models from forward propagation and backpropagation through CNNs, RNNs, VAEs, GANs, and Transformers, implementing them hands-on in TensorFlow/Keras and PyTorch.

• Coursera
• 7 weeks, 3 hours a week
• Self-Paced
• Paid Course

Generative AI Part 1

Study the mathematics behind neural networks: Adam and quasi-Newton optimization, dropout and batch normalization, CNNs, LSTM and GRU recurrent models, attention, and Transformer architectures.

• Coursera
• 7 weeks, 4 hours a week
• Self-Paced
• Paid Course

Arm Education

Getting Started with Machine Learning at the Edge on Arm

Train machine learning models and run them on Arm Cortex-M microcontrollers: neural networks, CNNs for audio and images, quantization, and the CMSIS-NN library with TensorFlow.

• Coursera
• 6 weeks, 2 hours a week
• Self-Paced
• Paid Course

Packt

Foundations of Model Optimization and Deep Learning

Tune machine learning models with grid search, random search, and Bayesian optimization, then build CNNs in Keras, TensorFlow, and PyTorch to classify Fashion MNIST images.

• Coursera
• 3 weeks, 2 hours a week
• Self-Paced
• Paid Course

Coursera

Deep Learning with PyTorch

Build deep learning models in PyTorch: implement feedforward networks, CNNs for image classification, RNNs and LSTMs for sequences, plus regularization, transfer learning, and training optimizations.

• Coursera
• 4 weeks, 7 hours a week
• Self-Paced
• Paid Course

Coursera

TensorFlow for Beginners: Basic Binary Image Classification

Build a convolutional neural network in TensorFlow to classify cat and dog images, tuning learning rate, batch size and epochs with data augmentation and dropout.

• Coursera
• 3 hours 12 minutes
• Self-Paced
• Paid Course

Packt

Advanced Machine Learning and Deep Learning

Build deep learning models for multi-target regression, classification, CNNs, autoencoders, transfer learning, and LSTM time-series prediction, then deploy interactive Shiny web applications.

• Coursera
• 8 weeks, 1 hour a week
• Self-Paced
• Paid Course

Packt

Foundations of Deep Learning and Neural Networks

Learn how neural networks work and train: perceptrons, feed-forward layers, activation functions, backpropagation with SGD, dropout and batch normalization, and CNNs in TensorFlow and Keras.

• Coursera
• 6 weeks, 2 hours a week
• Self-Paced
• Paid Course