AWS Machine Learning Foundations Course - Lesson 3 Flashcards
What is a machine learning task
The outputs of model training algorithms are classified based on the task they are designed to solve
How do you determine which machine learning task to use
The absence or presence of labeling in the the data is used to identify the machine learning task to use
What are the three components of machine learning
- A machine learning model
- A model training algorithm
- A model inference algorithm
What are the five machine learning steps
- Define the problem
- Build the dataset
- Train the model
- Evaluate the model
- Deploy/use the model
What are the four main machine learning tasks
- Supervised
- Unsupervised
- Semi - Supervised
- Reinforcement learning
How do you define machine learning
modern software development technique that enables computers to solve problems by using examples of real world data
What is the difference between a model parameter and a hyperparameter
Parameters are set and changed while hyperparameters are parameters of the algorithm itself, not of the model and cannot be changed
How would you define action
For every state, an agent needs to take an action toward achieving its goal
How would you define agent
The piece of software you are training is called an agent. It makes decisions in an environment to reach a goal
How would you define discriminator
A neural network trained to differentiate between real and synthetic (fake) data
How would yo define discriminator loss
Evaluates how well the discriminator differentiates between real and fake data
How would you define edit event
When a note is either added or removed from your input track during inference
How would you define environment
The environment is the surrounding area within which the agent interacts
Describe exploration vs. exploitation
An agent should exploit known information from previous experiences to achieve higher cumulative rewards, but it also needs to explore to gain new experiences that can be used in choosing the best actions in the future.
How would you define generator
A neural network that learns to create new data resembling the source data on which it was trained
How would you define generator loss
Measures how far the output data deviates from the real data present in the training dataset
How would you define hidden layer
A layer that occurs between the output and input layers. Hidden layers are tailored to a specific task.
How would you define input layer
The first layer in a neural network. This layer receives all data that passes through the neural network
How would you define output layer
The last layer in a neural network. This layer is where the predictions are generated based on the information captured in the hidden layers
How would you define piano roll
A two dimensional piano roll matrix that represents input tracks.
In a piano roll, how are time and pitch resented
Time is on the horizontal axis, and pitch is on the vertical axis
How would you define reward
Feedback is given to an agent for each actions it takes in a given state (as a numerical reward)
What is the AWS machine learning mission
To put machine learning in the hands of every developer
What is Amazon SageMaker
A fully managed service that removes complexity from machine learning workflows so every developer and data scientist can deploy machine learning for a wide range of use cases