Glossary of terms related to AI (Artificial Intelligence), ML (Machine Learning), and Deep Learning (DNN, Deep Neural Networks)

 

Glossary of terms related to AI (Artificial Intelligence)ning (DNN, Deep Neural Networks)

Glossary of terms related to AI (Artificial Intelligence), ML (Machine Learning), and Deep Learning (DNN, Deep Neural Networks):

AI (Artificial Intelligence):

1. Artificial Intelligence (AI): The broader field of computer science that aims to create systems capable of performing tasks that typically require human intelligence, such as problem-solving, understanding natural language, and recognising patterns.

Machine Learning (ML):

2. Machine Learning: A subset of AI that involves the development of algorithms that allow computers to learn from and make predictions or decisions based on data.

3. Supervised Learning: A type of machine learning where models are trained on labelled data, with input-output pairs, to make predictions or classifications.

4. Unsupervised Learning: A type of machine learning where models identify patterns and relationships in data without labelled outputs.

5. Reinforcement Learning: A type of machine learning where agents learn through trial and error, receiving rewards or penalties for their actions.

6. Feature Engineering: The process of selecting or transforming input data features to improve the performance of a machine learning model.

7. Overfitting: When a machine learning model learns the training data too well and performs poorly on unseen data due to excessive complexity.

8. Underfitting: When a machine learning model is too simple to capture the underlying patterns in the data and performs poorly on both training and test data.

9. Cross-Validation: A technique for assessing a model's performance by dividing data into multiple subsets for training and testing.

10. Bias-Variance Tradeoff: Balancing model simplicity (bias) and flexibility (variance) to achieve optimal generalization.

Deep Learning (DNN, Deep Neural Networks):

11. Deep Learning: A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn complex patterns from data.

12. Neural Network: A computational model inspired by the human brain, used for tasks such as image and speech recognition.

13. Artificial Neural Network (ANN): A computational model composed of interconnected nodes (neurons) organized into layers.

14. Deep Neural Network (DNN): A neural network with multiple hidden layers, allowing it to learn complex representations of data.

15. Convolutional Neural Network (CNN): A specialized neural network architecture for image and spatial data, featuring convolutional layers for feature extraction.

16. Recurrent Neural Network (RNN): A neural network architecture designed for sequential data, with feedback connections between neurons.

17. Long Short-Term Memory (LSTM): A type of RNN that mitigates the vanishing gradient problem and is well-suited for sequential data.

18. Gated Recurrent Unit (GRU): Another type of RNN that is more computationally efficient than LSTM.

19. Autoencoder: A neural network used for unsupervised learning that learns to reconstruct input data.

20. Transfer Learning: A technique where pre-trained neural network models are adapted for new tasks, saving training time and data.

This glossary should help you understand key terms in the fields of AI, ML, and deep learning. It's worth noting that these fields are dynamic, and new terminology and techniques continue to emerge as research and development progress.

  Thank You