Crowd-Curriculum by @rocksetta

Use mine and/or make your own!

Choose a Crowd Curriculum playlist

or

Teacher (login):
Teacher Password:

Your playlist ID's. Check the fields you want using the Show Everything playlist

My Email:
My Playlist Title:
My Public URL:
My Public Name:

End your data entries

Start Crowd-Curriculum entries
Note: To show all entries with a certain level, change the level and try http://rocksetta.com/crowd-curriculum/default.php?level=2.2
......ID:

(Leave ID blank to insert a record, enter the ID to edit a record or copy)

Leave Title blank to search for the above ID.

Title:

Level:

Short Explanation:

URL:

ImageURL:

Teacher owner of this entry:

ID	Title	T	Short Explanation	URL
89	Supervised Machine Learning	T	The program is trained on a pre-defined set of training examples, which then facilitate its ability to reach a % accuracy conclusion when given new data.
87	Regression Analysis	T	Systems where the value being predicted falls somewhere on a continuous spectrum.
92	Classification	T	Systems where we seek a yes-or-no prediction
90	Unsupervised Machine Learning	T	The program is given a bunch of data and must find patterns and relationships therein.
91	Neural Networks	T	Neural Networks are both software and hardware techniques loosely based on how the brain works and are the basis for Machine Learning.	https://www.toptal.com/machine-learning/an-introduction-to-deep-learning-from-perceptrons-to-deep-networks
93	Algorithms	T
94	Linear Algorithms	T
96	Gradient Descent	T		http://machinelearningmastery.com/gradient-descent-for-machine-learning/
97	Linear Regression	T		http://machinelearningmastery.com/linear-regression-for-machine-learning/
98	Logistic Regression	T		http://machinelearningmastery.com/logistic-regression-for-machine-learning/
99	Linear Discriminant Analysis	T		http://machinelearningmastery.com/linear-discriminant-analysis-for-machine-learning/
95	Non-Linear Algorithms	T
101	Classification And Regression Trees	T		http://machinelearningmastery.com/classification-and-regression-trees-for-machine-learning/
102	Naive Bayes	T		http://machinelearningmastery.com/naive-bayes-for-machine-learning/
103	K-Nearest Neighbors	T		http://machinelearningmastery.com/k-nearest-neighbors-for-machine-learning/
105	Learning Vector Quantization	T		http://machinelearningmastery.com/learning-vector-quantization-for-machine-learning/
106	Support Vector Machines	T		http://machinelearningmastery.com/support-vector-machines-for-machine-learning/
107	Bagging and Random Forest	T		http://machinelearningmastery.com/bagging-and-random-forest-ensemble-algorithms-for-machine-learning/
108	Boosting and AdaBoost	T		http://machinelearningmastery.com/boosting-and-adaboost-for-machine-learning/
149	Neuro-Evolution	T	neuroevolution, where neural networks are optimized through evolutionary algorithms, is also an effective method to train deep neural networks for reinforcement learning (RL) problems	https://eng.uber.com/deep-neuroevolution/
150	HTM (Hierarchical Temporal Memory)	T	At the core of HTM are learning algorithms that can store, learn, infer and recall high-order sequences. Unlike most other machine learning methods, HTM learns time-based patterns in unlabeled data on a continuous basis.	https://numenta.com/machine-intelligence-technology/

Title

Level

Short Explanation

URL

Supervised Machine Learning

 The program is trained on a pre-defined set of training examples, which then facilitate its ability to reach a % accuracy conclusion when given new data.

Regression Analysis

 Systems where the value being predicted falls somewhere on a continuous spectrum.

Classification

 Systems where we seek a yes-or-no prediction

Unsupervised Machine Learning

 The program is given a bunch of data and must find patterns and relationships therein.

Neural Networks

 Neural Networks are both software and hardware techniques loosely based on how the brain works and are the basis for Machine Learning.

https://www.toptal.com/machine-learning/an-introduction-to-deep-learning-from-perceptrons-to-deep-networks

Algorithms

Linear Algorithms

Gradient Descent

http://machinelearningmastery.com/gradient-descent-for-machine-learning/

Linear Regression

http://machinelearningmastery.com/linear-regression-for-machine-learning/

Logistic Regression

http://machinelearningmastery.com/logistic-regression-for-machine-learning/

Linear Discriminant Analysis

http://machinelearningmastery.com/linear-discriminant-analysis-for-machine-learning/

Non-Linear Algorithms

101

Classification And Regression Trees

http://machinelearningmastery.com/classification-and-regression-trees-for-machine-learning/

102

Naive Bayes

http://machinelearningmastery.com/naive-bayes-for-machine-learning/

103

K-Nearest Neighbors

http://machinelearningmastery.com/k-nearest-neighbors-for-machine-learning/

105

Learning Vector Quantization

http://machinelearningmastery.com/learning-vector-quantization-for-machine-learning/

106

Support Vector Machines

http://machinelearningmastery.com/support-vector-machines-for-machine-learning/

107

Bagging and Random Forest

http://machinelearningmastery.com/bagging-and-random-forest-ensemble-algorithms-for-machine-learning/

108

Boosting and AdaBoost

http://machinelearningmastery.com/boosting-and-adaboost-for-machine-learning/

149

Neuro-Evolution

 neuroevolution, where neural networks are optimized through evolutionary algorithms, is also an effective method to train deep neural networks for reinforcement learning (RL) problems

https://eng.uber.com/deep-neuroevolution/

150

HTM (Hierarchical Temporal Memory)

 At the core of HTM are learning algorithms that can store, learn, infer and recall high-order sequences. Unlike most other machine learning methods, HTM learns time-based patterns in unlabeled data on a continuous basis.

https://numenta.com/machine-intelligence-technology/

Use at your own risk
By Jeremy Ellis

Crowd-Curriculum by @rocksetta

Choose a Crowd Curriculum playlist

Use at your own riskBy Jeremy Ellis

Use at your own risk
By Jeremy Ellis