Machine Learning, Deep Learning, and Neural Networks

These flashcards cover key concepts in machine learning, deep learning, and neural networks, providing definitions for essential terms and theories.

Optimisation problems

Problems that involve finding the best solution from a set of alternatives.

Combinatorial optimisation problems (COP)

Problems that require finding the best combination of discrete values from a given set.

Travelling Salesman Problem (TSP)

A classic combinatorial optimisation problem (COP) where a salesperson must visit several cities, minimizing the travel distance.

Brute force approach

A straightforward method of solving a problem by trying every possible combination. (entails a combinatorial explosion)

Combinatorial explosion

A rapid increase in complexity when the number of possible combinations becomes too large to handle.

Curse of dimensionality

The phenomenon where an increase in data dimensions leads to an exponential increase in computational effort.

Heuristics

Clever shortcuts in the search process used to find good enough solutions when optimal ones are hard to compute.

Symbolic AI

An approach to artificial intelligence that uses logical reasoning and knowledge representation.

Connectionist AI

An approach to AI that mimics neural structures to create systems that learn through experience.

Deep learning

A subset of machine learning involving neural networks with many layers for modeling complex data.

Neural networks

Computational models inspired by biological neural networks, consisting of interconnected nodes (neurons).

Backpropagation algorithm

A method used in neural networks to minimize the error by adjusting the weights of connections.

Artificial Neural Network

A computational system modeled after the human brain, designed to recognize patterns and learn from data.

Reinforcement learning

A type of machine learning where agents learn to make decisions by receiving rewards or penalties.

Large Language Models (LLMs)

Mathematical functions designed to predict the next word in a sequence of text.

Deep reinforcement learning

A combination of deep learning and reinforcement learning techniques to solve complex tasks.