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.
Duration 8 hours
Course Outline
Foundations of Deep Learning
- Defining deep learning and its distinction from conventional machine learning
- Practical applications in computer vision, NLP, and other fields
- Survey of the deep learning ecosystem: TensorFlow 2.x, Keras, PyTorch
- Configuring a GPU-accelerated development setup
Underpinnings of Deep Learning
- Artificial neurons, activation functions, and network architectures
- Forward propagation and the calculation of predictions
- Loss functions tailored for classification and regression problems
- Optimization through gradient descent and the backpropagation process
- Training an initial neural network using the MNIST dataset
Convolutional Neural Networks in Computer Vision
- Concepts of convolution, filters, and feature maps
- Pooling layers and strategies for dimensionality reduction
- CNN structures: exploring LeNet, VGG, and ResNet principles
- Constructing and training a CNN for image classification
- Visualizing acquired features and intermediate activations
Data Augmentation and Model Precision
- How data augmentation mitigates overfitting and boosts generalization
- Image manipulations: rotation, flipping, zooming, and cropping
- Creating augmentation pipelines using Keras preprocessing layers
- Regularization methods such as dropout, batch normalization, and others
- Tracking training progress via validation metrics and early stopping
Transfer Learning via Pre-Trained Models
- The concept of transfer learning and its effectiveness
- Retrieving pre-trained models from Keras Applications (ResNet, EfficientNet, MobileNet)
- Feature extraction: fixing base layers and training new classifiers
- Fine-tuning: selectively unfreezing layers for domain-specific adaptation
- Achieving high accuracy with restricted training data
Recurrent Networks and Sequence Analysis
- Overview of sequential data and temporal dependencies
- Recurrent neural networks (RNNs) and the issue of vanishing gradients
- LSTM and GRU cells for managing long-range dependencies
- Training a character-level text generation model
- Word embeddings and the utilization of the Embedding layer in Keras
Core Natural Language Processing Concepts
- Text preparation: tokenization, padding, and constructing vocabularies
- Developing a text classifier using RNNs and LSTMs
- Sequence-to-sequence models for machine translation principles
- Attention mechanisms and their significance in contemporary NLP
- Practical NLP application using TensorFlow 2.x text processing APIs
Capstone Project: Image Captioning
- Integrating computer vision and NLP within a multimodal framework
- Extracting image features using a pre-trained CNN encoder
- Constructing an LSTM-based decoder for generating captions
- Handling multiple input layers via the Keras functional API
- Training and assessing the end-to-end captioning workflow
Future Directions and Resources
- Deploying trained models using TensorFlow Serving
- Investigating transformer architectures and large language models
- Advanced NVIDIA DLI workshops and certification tracks
- Community resources, datasets, and project suggestions
Requirements
- Fundamental command of Python programming (functions, loops, dictionaries, arrays)
- Understanding of programming constructs such as variables, conditionals, and data structures
- No previous experience in deep learning or machine learning is necessary
Target Audience
- Software developers and engineers moving into AI and machine learning roles
- Data analysts and data scientists aiming to acquire deep learning competencies
- Technical professionals intending to comprehend and implement neural network models
- Students and researchers starting their exploration of deep learning
Testimonials (2)
Getting people that never used AI some repetition in prompting and people that do use AI to consider different methods to using it.
Matthew Gay - Tarsus Pharmaceuticals
Course - Artificial Intelligence (AI) Overview
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
