AWS Machine Learning Module 2
Artificial Intelligence
Building machines that can perform tasks that a human would typically perform.
Features
Columns in ML (Machine Learning) problems.
Matplotlib
A library for creating scientific static, animated, and interactive visualizations in Python.
Hyperparameters
A parameter that can alter how the algorithm works.
Machine Learning
A subset of AI, which is a broad branch of computer science for building machines that can do human tasks.
JupyterLab
A web-based interactive development environment for Jupyter notebooks, code, and data.
Pandas
An open-source Python library. It's used for data handling and analysis. It represents data in a table that is similar to a spreadsheet.
Jupyter Notebook
An open-source web application that enables you to create and share documents that contain live code, equations, visualizations, and narrative text. Uses include data cleaning and transformation, numerical simulation, statistical modeling, data visualization, machine learning, and much more.
Seaborn
Another data visualization library for Python. It's built on matplotlib, and it provides a high-level interface for drawing informative statistical graphics.
Machine Learning
Broad branch of computer science that's focused on building machines that can do human tasks.
Deep Learning
Is a technique that was inspired from human biology. It uses layers of neurons to build networks that solve problems.
Machine Learning
It focuses on using data to train models so the models can make predictions.
Machine Learning
It is a sub-set of artificial intelligence or AI.
Scikit-Learn
It is an open source machine learning library that supports supervised and unsupervised learning. It also provides various tools for model fitting, data preprocessing, model selection and evaluation, and many other utilities.
Supervised Learning
Most popular type of ML because it's widely applicable.
NumPy
One of the fundamental scientific computing packages in Python. It contains functions for N-dimensional array objects and useful math functions such as linear algebra, Fourier transform, and random number capabilities.
Instances
Rows in ML (Machine Learning) problems.
Deep Learning
Sub-domain of Machine Learning.
Artificial Intelligence
The broad field of building machines to perform human tasks.
Features
The columns of data that you have within your dataset.
Underfitting
The model can't capture the relationship between the input examples (often called X) and the target values (often called Y).
Reinforcement Learning
The model learns in a way that is based on experience and feedback.
Overfitting
The model memorizes the data that it saw, and it can't generalize to unseen examples.
Python
The most popular language for performing machine learning tasks.
Feature Engineering
The process of selecting or creating the features that you will use to train your model.
Machine Learning
The scientific study of algorithms and statistical models to perform a task using inference rather than instructions.
Deep Learning
This represents a significant leap forward in the capabilities for AI (Artificial Intelligence) and ML (Machine Learning).
Supervised Learning
Type of machine learning where a model uses known inputs and outputs to generalize future outputs.
Unsupervised Learning
Type of machine learning where the model doesn't know inputs or outputs as it finds patterns in the data without help.
Reinforcement Learning
Type of machine learning where the model interacts with its environment and learns to take actions that maximize rewards.
Model Fit
Understanding this is important for finding the root cause for poor model accuracy.
Large datasets with a large number of variables
What are requirements for choosing machine learning as a development methodology?
Amazon SageMaker
Which Amazon service can you use to deploy machine learning instances and run Jupyter Notebooks?
pandas and scikit-learn
Which resources are Python libraries for working with machine learning problems?
Data preparation
Which stage of the machine learning pipeline involves verifying that your data is all of a uniform type?
The scientific study of algorithms and statistical models to preform tasks by using inference instead of instructions
Which statement describes machine learning?
Reinforcement Learning
Which type of training describes a machine learning application that interacts with its environment and learns to take actions that maximize rewards?
2012
Year where the use of neural networks began in the ImageNet Large Scale Visual Recognition Challenge, a machine learning competition for image recognition.
Multiclass Classification
You are creating a machine learning solution for a call center. The objective of the system is to route customers to the appropriate department, and there are wight possible departments. Which types of machine learning problem does this scenario describes?
Reinforcement learning
You are working on a machine learning problem that requires the system to respond to changes in the environment to improve performance. Which type of machine learning problem does this scenario describe?
Data preparation
You are working on a machine model that uses data from multiple countries. The countries are listed by using alphabetical abbreviations. Which stages involve converting these abbreviations to numerical values?
Unsupervised Learning
You have data, but you are looking for insights within the data.
Supervised Learning
You have training data for which you know the answer.
Underfitting
Your model is ______ the training data when the model performs poorly on the training data.
Overfitting
Your model is ______ your training data when it performs well on the training data, but it doesn't perform well on the evaluation data.
True
Your model is overfitting if it performs well on the training data, but not on the evaluation data.