Modules and Packages for Machine Learning with Python

Practice flashcards covering core vocabulary and concepts from the lecture on Python modules and packages for Machine Learning, including algebra, data manipulation, and deep learning libraries.

Vector

A quantity that has both magnitude and direction, represented in machine learning as an ordered list of numbers in an n-dimensional space.

Matrix

A two-dimensional table of numbers organized in rows and columns used to represent and manipulate data in machine learning and linear algebra.

Dot Product (Scalar Product)

An algebraic operation that takes two equal-length sequences of numbers and returns a single number, defined as $a \text{ . } b = a_1 \text{ . } b_1 + a_2 \text{ . } b_2 + a_3 \text{ . } b_3$.

NumPy

Short for 'Numerical Python', it is a fundamental library for scientific computing in Python that provides support for large, multi-dimensional arrays and matrices.

Pandas

An open-source Python library widely used for data analysis and manipulation, offering efficient structures like DataFrames and Series.

DataFrame

A two-dimensional, size-mutable, and potentially heterogeneous tabular data structure in Pandas with labeled axes (rows and columns).

Series

A one-dimensional labeled array in Pandas capable of holding any data type, which can be viewed as a single column of a DataFrame.

Machine Learning (ML)

A subfield of artificial intelligence focused on developing algorithms that allow computers to learn from data and make predictions without being explicitly programmed.

Supervised Learning

A type of machine learning where the model is trained on labeled data, meaning the input comes with the expected output or result.

Unsupervised Learning

A type of machine learning where the model is trained using data without labels to discover underlying patterns or structures.

Reinforcement Learning

A learning type where an agent learns to make decisions by interacting with an environment to maximize cumulative rewards.

Classification

A supervised learning task where the objective is to predict a discrete label or category, such as 'spam' or 'no spam'.

Regression

A supervised learning task where the objective is to predict a continuous numerical value, such as a house price.

Clustering

An unsupervised learning technique used to group data into clusters based on shared characteristics.

Cost Function

A function that a machine learning model seeks to minimize during training, such as the Mean Squared Error (MSE) in regression.

Hyperparameters

Parameters of a machine learning model that are set before the training process begins and are not learned directly from the data.

Scikit-Learn

A robust Python library for traditional machine learning that includes algorithms for classification, regression, clustering, and dimensionality reduction.

PyTorch

An open-source deep learning library developed by Facebook's AI Research lab (FAIR), known for its flexibility and dynamic computational graphs.

Tensors

Multi-dimensional data structures used in PyTorch (similar to NumPy arrays) that allow for efficient operations on GPUs.

Natural Language Processing (NLP)

A branch of AI focused on the interaction between computers and human language, enabling machines to understand and generate text.

Tokenization

The process of dividing text into smaller units called tokens, such as individual words, numbers, or punctuation marks.

NLTK (Natural Language Toolkit)

An open-source Python library designed specifically for working with human language data and performing tasks like sentiment analysis and tagging.

Deep Learning

A branch of machine learning based on artificial neural networks with multiple processing layers used to learn high-level data representations.

TensorFlow

An open-source library developed by Google for numerical computation and building complex machine learning models, especially neural networks.

Keras

A high-level neural networks API written in Python that acts as an interface for libraries like TensorFlow to facilitate rapid experimentation.

Sigmoid Function

An activation function that transforms inputs into a range between $0$ and $1$, represented as $\text{σ}(x) = \frac{1}{1 + e^{-x}}$.Matched as useful for binary classification.

ReLU (Rectified Linear Unit)

An activation function that returns zero for negative inputs and the input itself for positive values, defined as $f(x) = \text{max}(0, x)$.

Matplotlib

A comprehensive Python library for creating high-quality static, animated, and interactive visualizations.

Seaborn

A Python data visualization library based on Matplotlib that provides a high-level interface for drawing attractive and informative statistical graphics.

Histogram

A graphical representation of the distribution of a numerical variable, divided into intervals known as bins.