Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Introduction to Deep Learning
- Defining deep learning and distinguishing it from conventional machine learning
- Practical applications in computer vision, NLP, and other domains
- Survey of the deep learning landscape: TensorFlow 2.x, Keras, PyTorch
- Configuring a GPU-accelerated development setup
The Mechanics of Deep Learning
- Artificial neurons, activation functions, and network layers
- Forward propagation and the calculation of predictions
- Loss functions for classification and regression tasks
- Gradient descent optimization and backpropagation
- Training your initial neural network using the MNIST dataset
Convolutional Neural Networks for Computer Vision
- Comprehending convolution, filters, and feature maps
- Pooling layers and dimensionality reduction techniques
- CNN architectures: Concepts behind LeNet, VGG, and ResNet
- Constructing and training a CNN for image classification
- Visualizing learned features and intermediate activations
Data Augmentation and Enhancing Model Accuracy
- The role of data augmentation in preventing overfitting and boosting generalization
- Image transformation techniques: rotation, flipping, zooming, and cropping
- Implementing augmentation pipelines using Keras preprocessing layers
- Regularization methods such as dropout and batch normalization
- Monitoring training progress via validation metrics and early stopping strategies
Transfer Learning with Pre-Trained Models
- Understanding the concept of transfer learning and its effectiveness
- Loading pre-trained models from Keras Applications (ResNet, EfficientNet, MobileNet)
- Feature extraction: freezing base layers while training new classifiers
- Fine-tuning: selectively unfreezing layers for domain adaptation
- Attaining high accuracy with minimal training data
Recurrent Networks and Sequence Modeling
- Introduction to sequential data and temporal dependencies
- Recurrent neural networks (RNNs) and the vanishing gradient issue
- LSTM and GRU cells for handling long-range dependencies
- Training a character-level text generation model
- Word embeddings and the Embedding layer within Keras
Natural Language Processing Fundamentals
- Text preprocessing: tokenization, padding, and vocabulary construction
- Constructing a text classifier utilizing RNNs and LSTMs
- Concepts of sequence-to-sequence models for machine translation
- Attention mechanisms and their significance in contemporary NLP
- Practical NLP implementation with TensorFlow 2.x text processing APIs
Final Project: Image Captioning
- Merging computer vision and NLP within a multimodal architecture
- Extracting image features using a pre-trained CNN encoder
- Developing an LSTM-based decoder for caption generation
- Managing multiple input layers in the Keras functional API
- Training and evaluating the complete captioning pipeline
Next Steps and Resources
- Deploying trained models using TensorFlow Serving
- Exploring transformer architectures and large language models
- NVIDIA DLI advanced workshops and certification pathways
- Community resources, datasets, and project ideas
Requirements
- Foundational proficiency in Python programming (including functions, loops, dictionaries, and arrays)
- Understanding of programming concepts like variables, conditional statements, and data structures
- No previous experience in deep learning or machine learning is necessary
Target Audience
- Software developers and engineers transitioning into the fields of AI and machine learning
- Data analysts and data scientists aiming to acquire deep learning competencies
- Technical professionals interested in comprehending and applying neural network models
- Students and researchers initiating their exploration of deep learning
8 Hours
Testimonials (2)
The training was organized and well-planned out, and I come out of it with systematized knowledge and a good look at topics we looked at
Magdalena - Samsung Electronics Polska Sp. z o.o.
Course - Deep Learning with TensorFlow 2
I really liked the end where we took the time to play around with CHAT GPT. The room was not set up the best for this- instead of one large table a couple of small ones so we could get into small groups and brainstorm would have helped
