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 traditional machine learning
- Examining real-world applications in computer vision, NLP, and other domains
- Surveying the deep learning ecosystem: TensorFlow 2.x, Keras, and PyTorch
- Configuring a GPU-accelerated development environment
Core Mechanics of Deep Learning
- Exploring artificial neurons, activation functions, and network layers
- Understanding forward propagation and prediction computation
- Selecting appropriate loss functions for classification and regression
- Mastering gradient descent optimization and backpropagation
- Training an initial neural network using the MNIST dataset
Convolutional Neural Networks for Computer Vision
- Analyzing convolution, filters, and feature maps
- Utilizing pooling layers for dimensionality reduction
- Reviewing CNN architectures: LeNet, VGG, and ResNet concepts
- Developing and training a CNN for image classification
- Visualizing learned features and intermediate activations
Data Augmentation and Model Optimization
- Understanding how data augmentation mitigates overfitting and boosts generalization
- Applying image transformations: rotation, flipping, zooming, and cropping
- Creating augmentation pipelines using Keras preprocessing layers
- Incorporating dropout, batch normalization, and other regularization techniques
- Monitoring training progress with validation metrics and early stopping
Transfer Learning with Pre-Trained Models
- Conceptualizing transfer learning and its underlying principles
- Loading pre-trained models from Keras Applications (ResNet, EfficientNet, MobileNet)
- Performing feature extraction by freezing base layers and training new classifiers
- Applying fine-tuning: selectively unfreezing layers for domain adaptation
- Achieving high accuracy with constrained training data
Recurrent Networks and Sequence Modeling
- Introducing sequential data and temporal dependencies
- Examining recurrent neural networks (RNNs) and the vanishing gradient problem
- Employing LSTM and GRU cells for handling long-range dependencies
- Training a character-level text generation model
- Utilizing word embeddings and the Embedding layer in Keras
Natural Language Processing Fundamentals
- Handling text preprocessing: tokenization, padding, and vocabulary construction
- Developing a text classifier using RNNs and LSTMs
- Exploring sequence-to-sequence models for machine translation
- Analyzing attention mechanisms and their significance in modern NLP
- Practicing NLP with TensorFlow 2.x text processing APIs
Final Project: Image Captioning
- Merging computer vision and NLP into a multimodal architecture
- Extracting image features using a pre-trained CNN encoder
- Constructing an LSTM-based decoder for caption generation
- Managing multiple input layers via the Keras functional API
- Training and evaluating the complete captioning pipeline
Future Directions and Resources
- Deploying trained models with TensorFlow Serving
- Investigating transformer architectures and large language models
- Pursuing NVIDIA DLI advanced workshops and certification paths
- Accessing community resources, datasets, and project inspirations
Requirements
- Foundational proficiency in Python programming (functions, loops, dictionaries, arrays)
- Understanding of core programming concepts including variables, conditionals, and data structures
- No prior experience in deep learning or machine learning is necessary
Target Audience
- Software developers and engineers pivoting toward AI and machine learning
- Data analysts and scientists aiming to acquire deep learning capabilities
- Technical professionals interested in applying neural network models
- Students and researchers starting 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
