Here's a brief overview of each AI technique:

• Machine Learning: Machine learning involves training algorithms to recognise patterns from data. It can be supervised (predicting outcomes), unsupervised (finding patterns), or reinforcement (learning from rewards). Examples include predicting house prices, customer grouping, and game strategies. To know more, read the article by IBM.

  
  

• Natural Language Processing (NLP): NLP focuses on understanding and processing human language. It covers text analysis (sentiment assessment), speech recognition (voice assistants), and language translation. NLP techniques use tokenization, word embeddings, and language models like GPT. To know more, read the article by IBM.

  
  

• Machine Vision: Machine vision analyzes images or videos. It encompasses image classification (identifying objects), object detection (used in self-driving cars), and facial recognition. Techniques like convolutional neural networks (CNN) and transfer learning are applied. To know more, read the article by Intel.

  
  

• Other AI Techniques: Additional AI methods include expert systems (rule-based reasoning for medical diagnosis), genetic algorithms (optimising processes using evolutionary principles), and swarm intelligence (solving complex problems using collective behaviour). Examples are medical diagnosis, process optimisation, and route planning.

Each technique has distinct categories, use cases, and factors contributing to their effectiveness and applications.