Google Machine Learning Crash Course
The Market share of machine learning is increasing day by day, and so on until 2020, the market size is expected to increase by 85%. Many Educational Organizations and institutions are working to teach Machine Learning. Google Also introduced his machine learning Crash Course which helps the developer to enhance their knowledge in machine learning which is a subset of AI(Artificial intelligence).
Prerequisites
Machine Learning Crash Course does not assume or require any earlier information in AI. In any case, to comprehend the ideas displayed and complete the activities, we suggest that understudies meet the accompanying essentials:
Authority of introduction level variable based math. You ought to be OK with factors and coefficients, direct conditions, charts of capacities, and histograms. (Nature with further developed math ideas, for example, logarithms and subordinates is useful, yet not required.)
Capability in programming essentials, and some experience coding in Python. Programming practices in Machine Learning Crash Course are coded in Python utilizing TensorFlow. No related knowledge with TensorFlow is required, however, you should feel good perusing and composing Python code that contains essential programming develops, for example, work definitions/summons, records and circles, and restrictive articulations.
This course covers the three modules which include the following topics in this area. The total duration of this course is 15 hours which has 25 lessons and more than 40 exercises.
ML CONCEPTS
introduction to ml
Framing
Descending into ML
Reducing Loss
First Steps with TF
Generalization
Training and Test Sets
Validation Set
Representation
Feature Crosses
Regularization: Simplicity
Logistic Regression
Classification
Regularization: Sparsity
Neural Networks
Training Neural Nets
Multi-Class Neural Nets
Embedding
ML ENGINEERING
Production ML Systems
Static VS Dynamic Training
Static VS Dynamic Interence
Data Dependencies
Fairness
ML SYSTEMS IN THE REAL WORLD
Cancer Prediction
Literature
Guidelines
