Pattern Recognition, Neural Networks & Deep Learning

Learning Outcomes:

• Understanding the fundamental concepts and techniques of pattern recognition and machine learning
• Analyzing datasets to extract relevant features for classification tasks
• Implementing linear and nonlinear classifiers like perceptrons and support vector machines
• Designing and training artificial neural networks for various learning tasks
• Applying dimensionality reduction techniques like PCA to preprocess high-dimensional data
• Evaluating the performance of machine learning models using appropriate metrics
• Implementing ensemble methods like bagging and boosting to improve classifier accuracy
• Utilizing deep learning architectures like convolutional neural networks for complex tasks
• Comparing different machine learning algorithms to select the most suitable for a given problem
• Interpreting the internal representations learned by deep neural networks
• Addressing common issues in machine learning like overfitting and class imbalance
• Implementing generative models like GANs to create synthetic data
• Applying transfer learning to leverage pretrained models for new tasks

Skills for module:

Python

R

Matlab

Object Oriented Programming

Functional Programming

Machine Learning

Deep Learning

Artificial Intelligence

Reinforcement Learning

Intelligent Agents

Data Science

Hyperparameters

Boosting

Data Visualisation

Neural Networks

Computer Vision

Scikit Learn

Pandas

NumPy

Matplotlib

Seaborn

Keras

TensorFlow

PyTorch

Jupyter Notebooks

Probability

Statistics

Calculus

Linear Algebra

Algorithms

Data Structures

Problem Solving

Critical Thinking

Time Management

Continuous Integration

Mathematics