Getting to know the toolkit serves as an appetizer before the Main course of Machine Learning.
Jupyter notebooks: Interactive Coding and Visualization of Output.
NumPy, SciPy, Pandas: Numerical Computation
Matplotlib, Seaborn: Data Visualization
Polyglot analysis environment — blends multiple languages
Jupyter is an anagram of Julia, Python, and R
Supports multiple content types: code, narrative text, images, movies, etc.
Code is divided into cells to control execution
Enables interactive development
Ideal for exploratory analysis and model building
%matplotlib inline: display plots inline in Jupyter notebook
%%timeit: time how long a cell takes to execute
The above single image given by Intel site is telling so many things about the future/importance of AI for all industries.
Industries are making decisions quickly and more accurately for adopting AI.
Below are the section wise business modules using AI for better Market opportunity.
The model may turn out to be far too complex if we continuously keep adding more variables.
Will fail to simplify as it is memorizing the training data.
We say Model is over-fitting when the accuracy is high in Training and the accuracy of Test is very low
Associations between predictor variables. Single Variable collinearity can be existing with two or more variable even if no pair of variables has a high correlation.
Multicollinearity affects when we are trying to interpret the model, we can avoid by checking Pairwise Correlations and by Variance Inflation Factor (VIF) value.
Maximum time we used to get the questions for machine learning is what types of Math should we should learn and reasons behind this question could be many.
But yes, if we know the few topics from Math then we can apply that knowledge in Model building or in further research in a better way.
When you will start to learn Machine Learning, you will start to like math way more than ever, you will realize it’s truly just applied math and math is actually just the semantic in nature so Machine learning is one part linear algebra and one…
Estimating the true cost in cloud computing is not so easy, sometimes annoying.
So many components like CPUs, memory, storage, and network bandwidth that need to be consider for proposed workload for which we required to estimate the Cost in the cloud.
But Data is an important part in the billing and for getting Data into the Cloud is usually free but getting data out is a completely different story, cloud vendors charge for data egress (Data Out).
Technical specialist for AI & ML . Cloud (Oracle Cloud Infrastructure/Azure/AWS) . AEM . DevOps