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
Introduction to Deep Learning
- Defining deep learning and its distinctions from conventional machine learning
- Practical applications in computer vision, NLP, and other domains
- A snapshot of the deep learning landscape, including TensorFlow 2.x, Keras, and PyTorch
- Configuring a GPU-optimized development workspace
How Deep Learning Works
- Exploring artificial neurons, activation functions, and layer structures
- The process of forward propagation and generating predictions
- Loss functions tailored for both classification and regression challenges
- Optimization techniques via gradient descent and backpropagation
- Constructing and training your initial neural network using the MNIST dataset
Convolutional Networks for Visual Analysis
- Decoding the concepts of convolution, filters, and feature extraction
- The role of pooling layers in reducing data dimensions
- Key CNN architectural patterns, such as LeNet, VGG, and ResNet
- Building and training a CNN for image categorization
- Visualizing the features learned through intermediate network activations
Enhancing Accuracy via Data Augmentation
- How data augmentation mitigates overfitting and boosts generalization
- Common image manipulations, including rotation, mirroring, scaling, and cropping
- Creating augmentation workflows using Keras preprocessing layers
- Regularization strategies like dropout and batch normalization
- Monitoring training progress using validation metrics and early stopping mechanisms
Transfer Learning Strategies
- The principles behind transfer learning and its effectiveness
- Utilizing pre-trained architectures from Keras Applications (e.g., ResNet, EfficientNet, MobileNet)
- Feature extraction workflows, including freezing base layers and training new heads
- Fine-tuning processes, such as selectively unfreezing layers for specific domains
- Achieving superior accuracy with minimal training datasets
Sequential Modeling with Recurrent Networks
- Understanding time-series data and temporal relationships
- RNN architectures and the challenges of vanishing gradients
- LSTM and GRU units for capturing long-term dependencies
- Training a model for character-by-character text generation
- Implementing word embeddings and utilizing the Keras Embedding layer
Essentials of Natural Language Processing
- Text preparation steps, including tokenization, padding, and vocabulary creation
- Developing text classifiers using RNNs and LSTMs
- Concepts behind sequence-to-sequence models for translation tasks
- The function of attention mechanisms in contemporary NLP systems
- Applying TensorFlow 2.x text processing APIs for practical NLP tasks
Capstone Project: Image Caption Generation
- Integrating computer vision and NLP into a unified multimodal framework
- Extracting visual features using a pre-trained CNN encoder
- Designing an LSTM-based decoder for generating image descriptions
- Handling multiple input streams via the Keras Functional API
- Training and assessing the complete end-to-end captioning workflow
Future Pathways and Learning Resources
- Serving trained models using TensorFlow Serving
- Investigating transformer architectures and large language models
- NVIDIA DLI advanced workshops and professional certification tracks
- Access to community tools, public datasets, and project inspiration
Requirements
- Fundamental competence in Python scripting, including functions, loops, dictionaries, and arrays
- Knowledge of core programming logic, such as variables, conditional structures, and data types
- No previous background in deep learning or machine learning is necessary
Target Audience
- Software developers and engineers aiming to pivot into AI and machine learning roles
- Data analysts and scientists looking to acquire deep learning expertise
- Technical professionals eager to comprehend and deploy neural network models
- Students and researchers starting their academic or professional journey in 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
