Introduction to Machine Learning – Vocabulary Flashcards

A comprehensive set of vocabulary flashcards covering key terms from the lecture on biological vs. artificial neurons, machine-learning fundamentals, architectures, characteristics, and learning paradigms.

Biological Neuron

A nerve cell in the human cortex that communicates via electrical spikes; roughly 10 billion exist and each connects to thousands of other neurons.

Dendrites

Branch-like structures of a neuron that receive signals from other neurons.

Soma

The cell body of a neuron that houses essential components such as the nucleus.

Nucleus (Neuron)

The control center within the neuron’s soma that regulates cellular activity.

Axon

A neuron fiber that carries nerve impulses away from the cell body toward other neurons or muscles.

Axon Terminal Button

Small knobs at the end of an axon that release neurotransmitters to communicate with adjacent cells.

Artificial Neuron

An information-processing unit in an ANN that receives weighted inputs, applies an activation function, and produces an output.

Connection Weight

A numerical value that scales the signal passed between two artificial neurons, indicating connection strength.

Activation Function

A (typically nonlinear) function applied to a neuron’s net input to determine its output signal.

Learning Rule

A procedure for adjusting connection weights in an ANN to minimize error and solve a task.

Input Layer

The first layer of an ANN responsible for receiving external data and passing it to the network.

Hidden Layer

Intermediate ANN layer(s) that perform computations and transform inputs before reaching the output layer.

Output Layer

The final layer of an ANN that delivers the network’s predictions or decisions to the outside world.

Artificial Intelligence (AI)

A computer-science field focused on creating systems that think, work, and react like humans.

Machine Learning (ML)

A subset of AI that enables computers to learn patterns from data without explicit programming.

Deep Learning

A sub-field of ML that uses many layered neural networks to learn hierarchical representations of data.

Natural Language Processing (NLP)

Techniques that enable computers to understand, interpret, and generate human language.

Predictive Analytics

The use of data, statistical algorithms, and ML to identify the likelihood of future outcomes.

Pattern Recognition

The automated identification of regularities or patterns in data, often via ML algorithms.

Machine Vision

The application of computer vision techniques for automated image analysis and interpretation.

Robotics

The branch of technology dealing with the design and operation of robots, often leveraging AI and ML.

Single-Layer Network

An ANN architecture with one processing (output) layer directly connected to the inputs.

Multi-Layer Network

An ANN containing one or more hidden layers between the input and output layers.

Black Box Model

A predictive ML model whose internal workings are not easily interpretable despite high accuracy.

Automated Data Visualization

ML-driven tools that automatically generate visual insights from structured or unstructured data.

Scalability (ML Systems)

The ability of an ML system to handle growing amounts of data or complexity efficiently.

Ensemble Modelling

Combining multiple ML models to improve predictive performance over any single model.

Supervised Learning

ML paradigm where models are trained on labeled data containing input–output pairs.

Unsupervised Learning

ML paradigm that finds patterns or groupings in unlabeled data without predefined outputs.

Semi-Supervised Learning

ML approach that uses a small amount of labeled data along with a large amount of unlabeled data.

Reinforcement Learning

Learning paradigm in which an agent learns optimal actions through rewards obtained from interactions with an environment.

Cluster Analysis

An unsupervised technique that groups data points based on similarity metrics such as Euclidean distance.

Euclidean Distance

A common metric for measuring straight-line similarity between two points in multidimensional space.

Iris Data Set

A classic labeled data set containing flower measurements for three Iris species, often used to illustrate supervised learning.

Parallel Distributed Processors

Another term for artificial neural networks emphasizing simultaneous computation across many interconnected units.

Biological Neuron

A nerve cell in the human cortex that communicates via electrical spikes; roughly $10$ billion exist and each connects to thousands of other neurons.

Dendrites

Branch-like structures of a neuron that receive signals from other neurons.

Soma

The cell body of a neuron that houses essential components such as the nucleus.

Nucleus (Neuron)

The control center within the neuron

f
s Soma that regulates cellular activity.

Axon

A neuron fiber that carries nerve impulses away from the cell body toward other neurons or muscles.

Axon Terminal Button

Small knobs at the end of an axon that release neurotransmitters to communicate with adjacent cells.

Artificial Neuron

An information-processing unit in an ANN that receives weighted inputs, applies an activation function, and produces an output.

Connection Weight

A numerical value that scales the signal passed between two artificial neurons, indicating connection strength.

Activation Function

A (typically nonlinear) function applied to a neuron

f
s net input to determine its output signal.

Learning Rule

A procedure for adjusting connection weights in an ANN to minimize error and solve a task.

Input Layer

The first layer of an ANN responsible for receiving external data and passing it to the network.

Hidden Layer

Intermediate ANN layer(s) that perform computations and transform inputs before reaching the output layer.

Output Layer

The final layer of an ANN that delivers the network

f
s predictions or decisions to the outside world.

Artificial Intelligence (AI)

A computer-science field focused on creating systems that think, work, and react like humans.

Machine Learning (ML)

A subset of AI that enables computers to learn patterns from data without explicit programming.

Deep Learning

A sub-field of ML that uses many layered neural networks to learn hierarchical representations of data.

Natural Language Processing (NLP)

Techniques that enable computers to understand, interpret, and generate human language.

Predictive Analytics

The use of data, statistical algorithms, and ML to identify the likelihood of future outcomes.

Pattern Recognition

The automated identification of regularities or patterns in data, often via ML algorithms.

Machine Vision

The application of computer vision techniques for automated image analysis and interpretation.

Robotics

The branch of technology dealing with the design and operation of robots, often leveraging AI and ML.

Single-Layer Network

An ANN architecture with one processing (output) layer directly connected to the inputs.

Multi-Layer Network

An ANN containing one or more hidden layers between the input and output layers.

Black Box Model

A predictive ML model whose internal workings are not easily interpretable despite high accuracy.

Automated Data Visualization

ML-driven tools that automatically generate visual insights from structured or unstructured data.

Scalability (ML Systems)

The ability of an ML system to handle growing amounts of data or complexity efficiently.

Ensemble Modelling

Combining multiple ML models to improve predictive performance over any single model.

Supervised Learning

ML paradigm where models are trained on labeled data containing input

f
output pairs.

Unsupervised Learning

ML paradigm that finds patterns or groupings in unlabeled data without predefined outputs.

Semi-Supervised Learning

ML approach that uses a small amount of labeled data along with a large amount of unlabeled data.

Reinforcement Learning

Learning paradigm in which an agent learns optimal actions through rewards obtained from interactions with an environment.

Cluster Analysis

An unsupervised technique that groups data points based on similarity metrics such as Euclidean distance.

Euclidean Distance

A common metric for measuring straight-line similarity between two points in multidimensional space.

Iris Data Set

A classic labeled data set containing flower measurements for three Iris species, often used to illustrate supervised learning.

Parallel Distributed Processors

Another term for artificial neural networks emphasizing simultaneous computation across many interconnected units.

Perceptron

The simplest type of ANN, a single-layer network that performs binary classification based on a linear decision boundary.

Backpropagation

An algorithm used to train feedforward neural networks by calculating the gradient of the loss function with respect to each weight and adjusting weights to minimize error.

Loss Function

A function that quantifies the difference between the predicted output of a model and the actual target value, guiding the learning process.

Feedforward Neural Network

A type of artificial neural network where connections between nodes do not form a cycle, meaning information flows only in one direction, from input to output.

Biological Neuron

A nerve cell in the human cortex that communicates via electrical spikes; roughly $10$ billion exist and each connects to thousands of other neurons.

Dendrites

Branch-like structures of a neuron that receive signals from other neurons.

Soma

The cell body of a neuron that houses essential components such as the nucleus.

Nucleus (Neuron)

The control center within the neuron’s Soma that regulates cellular activity.

Axon

A neuron fiber that carries nerve impulses away from the cell body toward other neurons or muscles.

Axon Terminal Button

Small knobs at the end of an axon that release neurotransmitters to communicate with adjacent cells.

Artificial Neuron

An information-processing unit in an ANN that receives weighted inputs, applies an activation function, and produces an output.

Connection Weight

A numerical value that scales the signal passed between two artificial neurons, indicating connection strength.

Activation Function

A (typically nonlinear) function applied to a neuron’s net input to determine its output signal.

Learning Rule

A procedure for adjusting connection weights in an ANN to minimize error and solve a task.

Input Layer

The first layer of an ANN responsible for receiving external data and passing it to the network.

Hidden Layer

Intermediate ANN layer(s) that perform computations and transform inputs before reaching the output layer.

Output Layer

The final layer of an ANN that delivers the network’s predictions or decisions to the outside world.

Artificial Intelligence (AI)

A computer-science field focused on creating systems that think, work, and react like humans.

Machine Learning (ML)

A subset of AI that enables computers to learn patterns from data without explicit programming.

Deep Learning

A sub-field of ML that uses many layered neural networks to learn hierarchical representations of data.

Natural Language Processing (NLP)

Techniques that enable computers to understand, interpret, and generate human language.

Predictive Analytics

The use of data, statistical algorithms, and ML to identify the likelihood of future outcomes.

Pattern Recognition

The automated identification of regularities or patterns in data, often via ML algorithms.

Machine Vision

The application of computer vision techniques for automated image analysis and interpretation.

Robotics

The branch of technology dealing with the design and operation of robots, often leveraging AI and ML.

Single-Layer Network

An ANN architecture with one processing (output) layer directly connected to the inputs.

Multi-Layer Network

An ANN containing one or more hidden layers between the input and output layers.

Black Box Model

A predictive ML model whose internal workings are not easily interpretable despite high accuracy.

Automated Data Visualization

ML-driven tools that automatically generate visual insights from structured or unstructured data.

Scalability (ML Systems)

The ability of an ML system to handle growing amounts of data or complexity efficiently.