Deep Learning - Revision history

Techbot: /* Definition */

2022-03-10T21:17:00Z

Definition

← Older revision		Revision as of 23:17, 10 March 2022
Line 1:		Line 1:

	===== Definition =====		===== Definition =====
			Deep Learning is a subset of A.I
			Although applicable accoss many domains and disciplines we will be concentrating solely on audio. Even here we will be ignoring such topics as audio classification and and concentrating on generation and composition, and to a lesser extend de-mixing and audio restoration.

			Peter Kirn http://cdm.link/2019/04/now-ai-takes-on-writing-death-metal-country-music-hits-more/

	In traditional problem-solving with software, a person analyzes a problem and engineers a solution in code to solve that problem.		In traditional problem-solving with software, a person analyzes a problem and engineers a solution in code to solve that problem.
	In machine learning the problem solver abstracts away part of their solution as a flexible component called a model, and uses a special program called a model training algorithm to adjust that model to real-world data. The result is a trained model which can be used to predict outcomes that are not part of the data set used to train it.		In machine learning the problem solver abstracts away part of their solution as a flexible component called a model, and uses a special program called a model training algorithm to adjust that model to real-world data. The result is a trained model which can be used to predict outcomes that are not part of the data set used to train it.

Techbot at 14:03, 21 February 2022

2022-02-21T14:03:49Z

Show changes

Techbot: Replaced content with "here"

2021-12-12T11:50:11Z

Replaced content with "here"

Show changes

Techbot: /* Python */

2021-10-11T18:33:49Z

Python

← Older revision		Revision as of 20:33, 11 October 2021
Line 184:		Line 184:

	= Python =		= Python =
			There are several essential tools in the [[Python]] kit for Deep Learning
	[[Librosa]] is used to analyse and manipulate audio		[[Librosa]] is used to analyse and manipulate audio

Techbot: /* Architectural Patterns */

2021-10-11T13:10:22Z

Architectural Patterns

@@ Line 136: / Line 136: @@
      * Using a trained model.
      * Testing your model on data it has not seen before.
 = Architectural Patterns =
@@ Line 156: / Line 182: @@
 • recurrent (RNN).
 = Python =

Techbot: /* Reinforcement Learning */

2021-10-11T12:48:38Z

Reinforcement Learning

← Older revision		Revision as of 14:48, 11 October 2021
Line 44:		Line 44:

	* The reward function's purpose is to encourage the agent to reach its goal. Figuring out how to reward which actions is one of your most important jobs.		* The reward function's purpose is to encourage the agent to reach its goal. Figuring out how to reward which actions is one of your most important jobs.

			The more an agent learns about its environment, the more confident it becomes about the actions it chooses.

			If an agent doesn't explore enough, it often sticks to information its already learned even if this knowledge doesn't help the agent achieve its goal.

			The agent can use information from previous experiences to help it make future decisions that enable it to reach its goal.

	== Machine Learning steps for music generation ==		== Machine Learning steps for music generation ==

Techbot: /* Reinforcement Learning */

2021-10-11T12:47:02Z

Reinforcement Learning

← Older revision		Revision as of 14:47, 11 October 2021
Line 23:		Line 23:
	==Reinforcement Learning==		==Reinforcement Learning==
	In reinforcement learning, the algorithm figures out which actions to take in a situation to maximize a reward (in the form of a number) on the way to reaching a specific goal.		In reinforcement learning, the algorithm figures out which actions to take in a situation to maximize a reward (in the form of a number) on the way to reaching a specific goal.

			An agent is a piece of software you are training that makes decisions in an environment to reach a goal.

	* An algorithm is a set of instructions that tells a computer what to do. ML is special because it enables computers to learn without being explicitly programmed to do so.		* An algorithm is a set of instructions that tells a computer what to do. ML is special because it enables computers to learn without being explicitly programmed to do so.

Techbot: /* Reinforcement Learning */

2021-10-11T12:44:28Z

Reinforcement Learning

← Older revision		Revision as of 14:44, 11 October 2021
Line 39:		Line 39:

	* Hyperparameters are variables that control the performance of your agent during training. There is a variety of different categories with which to experiment. Change the values to increase or decrease the influence of different parts of your model.		* Hyperparameters are variables that control the performance of your agent during training. There is a variety of different categories with which to experiment. Change the values to increase or decrease the influence of different parts of your model.
	For example, the learning rate is a hyperparameter that controls how many new experiences are counted in learning at each step. A higher learning rate results in faster training but may reduce the model’s quality.		# * For example, the learning rate is a hyperparameter that controls how many new experiences are counted in learning at each step. A higher learning rate results in faster training but may reduce the model’s quality.

	* The reward function's purpose is to encourage the agent to reach its goal. Figuring out how to reward which actions is one of your most important jobs.		* The reward function's purpose is to encourage the agent to reach its goal. Figuring out how to reward which actions is one of your most important jobs.

Techbot: /* Reinforcement Learning */

2021-10-11T12:43:17Z

Reinforcement Learning

← Older revision		Revision as of 14:43, 11 October 2021
Line 34:		Line 34:
	* An action space is the set of all valid actions, or choices, available to an agent as it interacts with an environment.		* An action space is the set of all valid actions, or choices, available to an agent as it interacts with an environment.

	* Discrete action space represents all of an agent's possible actions for each state in a finite set of steering angle and throttle value combinations.		# * Discrete action space represents all of an agent's possible actions for each state in a finite set of steering angle and throttle value combinations.
			#
			# Continuous action space allows the agent to select an action from a range of values that you define for each state.

	~~Continuous action space allows~~ the agent ~~to select an action from~~ a ~~range~~ of values that ~~you define for~~ each ~~state~~.		* Hyperparameters are variables that control the performance of your agent during training. There is a variety of different categories with which to experiment. Change the values to increase or decrease the influence of different parts of your model.
			For example, the learning rate is a hyperparameter that controls how many new experiences are counted in learning at each step. A higher learning rate results in faster training but may reduce the model’s quality.

	Hyperparameters are variables that control the performance of your agent during training. There is a variety of different categories with which to experiment. Change the values to increase or decrease the influence of different parts of your model.		* The reward function's purpose is to encourage the agent to reach its goal. Figuring out how to reward which actions is one of your most important jobs.
	For example, the learning rate is a hyperparameter that controls how many new experiences are counted in learning at each step. A higher learning rate results in faster training but may reduce the model’s quality.

	The reward function's purpose is to encourage the agent to reach its goal. Figuring out how to reward which actions is one of your most important jobs.

	== Machine Learning steps for music generation ==		== Machine Learning steps for music generation ==

Techbot: /* Reinforcement Learning */

2021-10-11T12:42:09Z

Reinforcement Learning

← Older revision		Revision as of 14:42, 11 October 2021
Line 28:		Line 28:
	* The training algorithm defines your model’s learning objective, which is to maximize total cumulative reward. Different algorithms have different strategies for going about this.		* The training algorithm defines your model’s learning objective, which is to maximize total cumulative reward. Different algorithms have different strategies for going about this.

	* * A soft actor critic (SAC) embraces exploration and is data-efficient, but can lack stability.		# * A soft actor critic (SAC) embraces exploration and is data-efficient, but can lack stability.
			#
	* * A proximal policy optimization (PPO) is stable but data-hungry.		# * A proximal policy optimization (PPO) is stable but data-hungry.

	* An action space is the set of all valid actions, or choices, available to an agent as it interacts with an environment.		* An action space is the set of all valid actions, or choices, available to an agent as it interacts with an environment.