Skip to main content

How To Break Into Machine Learning?

How To Break Into Machine Learning?

The trend of using machine learning to solve problems is increasing in almost every field such as medicine, business, research, etc. So, for the present day it has become like an essential skill to be learn. To break into machine learning, my advice is to follow the following steps:


  • Step-1: Make Your Mindset. The first and most important step towards learning the machine learning is to prepare yourself mentally to begin your journey. Believe in yourself and increase trust. Think, why are you interested in learning Machine Learning and what is your goal? This will help you a lot to keep track of your journey in the right direction.

  • Step-2:Learn basics of R/Python.There are multiple languages that can be used for solving machine learning problems. However, these days “R” and “Python” are the most commonly used languages and there is enough resources & Learning communities available for both. Before you get involved into world of ML, you must have some basic knowledge and hands on programming in one of these two languages (R or Python) which can help to focus on machine learning and with this node you can start your journey towards become ML expert
     
  • Step-3: Learn Basic Mathematics. Since Machine Learning includes much of the mathematical uses for interpretation and optimization so one must have sound  knowledge of mathematics before starting core algorithms of Machine Learning. The topics to be covered on Mathematics for Machine Learning are
                   Linear Algebra
                   Probability & Statistics
                   Calculus

You can find tons of online resources for studying these topics of mathematics.Some of the online resources for studying mathematics for Machine Learning are:


· Khan Academy’s Linear Algebra, Probability & Statistics, Multivariable Calculusand Optimization.
· Linear Algebra — Foundations to Frontiers by Robert van de Geijn, University of Texas.
· Applications of Linear Algebra, Part 1 and Part 2. A newer course by Tim Chartier, Davidson College.
· Joseph Blitzstein — Harvard Stat 110 lectures.
· Boyd and Vandenberghe’s course on Convex optimization from Stanford.
· Linear Algebra — Foundations to Frontiers on edX.


Once you have good knowledge of mathematics required for Machine Learning you should learn how to implement the mathematics through the programming language. For this you should have good practice and knowledge about the libraries used for mathematical computing in  Machine Learning. For example, if you have switched to python there are Libraries as Scipy, Numpy, Pandas etc. there might be similar libraries in R also. You have to learn how to use those libraries according to your requirement in the problem.
  • Step-4: Learn Data Handling (Preparation/Interpretation/Analysis).


This is  the first and one of the most important step of the machine Learning where in you are tend to do almost 80% of the whole work which is known as Data Pre-Processing. If you have good practice on data pre-processing and data analysis then you are less likely to have defects in your Machine Learning models and Predictions made by them.
The fact is that more you  clean and pre-process your data as per your business cases or requirement, the better your chance of success are. To become a good ML expert from an average, one should have sound practice of feature engineering and data cleaning which happens on the original data.
Data preparation includes preparing your data to apply machine learning algorithms on them. Supplied data might not be proper and complete and might need to be cleaned. Data Cleaning can be defined as the process of inserting most appropriate data in the empty places by using mathematical techniques like interpolation, filling with mean or median values etc.
Once you have cleaned your data, you need to interpret it and visualize it to know about the features which contain important information about the data. This step is very interesting and is used to explain the data via analysis (Using dashboards, Charts and Diagrams, Histograms). Usually we have a large amount of data so visual analysis is done to understand the data more clearly. Industry Expert use this phase by putting up dashboards using analytical tools (using Tableau) for exploring the data and to give valuable insights for the same based on your business use case. In some cases you might need to make your own feature from previous ones  which is called feature engineering.
Python contains the libraries, like Pandas that contains strong tools(Functions) for data cleaning and pre-processing. In the same way Matplotlib and seaborn are the libraries of python that provides tools for data visualizations.


  •  Step-5: Learn basic Machine learning algorithms. Here comes the starting of core of machine learning. First of all you need to learn the basics algorithms of  machine learning.

Here is the list of commonly used machine learning algorithms. These algorithms can be applied to almost any data problem:
    1. Linear Regression
    2. Logistic Regression
    3. Decision Tree
    4. SVM
    5. Naive Bayes
    6. kNN
    7. K-Means
    8. Random Forest
    9. Dimensionality Reduction Algorithms
    10. Gradient Boosting algorithms
      1. GBM
      2. XGBoost
      3. LightGBM
      4. CatBoost
     You can get dozens of online resources to study about their alogrithms and how to implement using Python/R. Some of the best materials on youtube includes Victer Lavernko, Paul G. Allen School, Andrew ng, Siraj Raval, Sentdex and many others.In addition to these free materials you can also take online paid courses that provides you learning certificates. Some of such online learning platforms are Udemy, Coursera, etc. You can also find several books dealing to the algorithms of machine in internet.

    Description


           
  • Step-5: Learn Advance Machine learning algorithms. Once you have mastered in basic topics, then you can go for some of the advance and specialized topics like Deep learning, Reinforcement learning. You can find the materials on these topics over internet easily. Studying and practicing these topics will make you expert in the field of machine learning.

Labels:

Comments

Post a Comment

Popular posts from this blog

Understanding KNN(K-nearest neighbor) with example

Understanding KNN(K-nearest neighbor) with example.  It is probably, one of the simplest but strong supervised learning algorithms used for classification as well regression purposes. It is most commonly used to classify the data points that are separated into several classes, in order to make prediction for new sample data points. It is a non-parametric and lazy learning algorithm. It classifies the data points based on the similarity measure (e.g. distance measures, mostly Euclidean distance). Assumption of KNN : K- NN algorithm is based on the principle that, “the similar things exist closer to each other or Like things are near to each other.” In this algorithm ‘K’ refers to the number of neighbors to consider for classification. It should be odd value.  The value of ‘K’ must be selected carefully otherwise it may cause defects in our model. If the value of ‘K’ is small then it causes Low Bias, High variance i.e. over fitting of model. In the same way if ‘K’ is v...
Post a Comment
Read more

Implementation Of KNN (From Scratch in PYTHON)

Implementation Of KNN (From Scratch in PYTHON) Implementation Of KNN (From Scratch in PYTHON) KNN classifier is one of the simplest but strong supervised machine learning algorithm. It can  be used for both classification and regression problems. There are some libraries in python to implement KNN, which allows a programmer to make KNN model easily without using deep ideas of mathematics. But if we try to implement KNN from scratch it becomes a bit tricky. Before getting into the program lets recall the algorithm of KNN: Algorithm for K-NN: 1.     Load the given data file into your program 2.     Initialize the number of neighbor to be considered i.e. ‘K’ (must be odd). 3.     Now for each tuples (entries or data point) in the data file we perform:                        i.     Calculate distance between the data point (tuple) to be classified and each data points in the gi...
Post a Comment
Read more

Supervised Machine Learning

Supervised Machine Learning What Is Supervised Learning?  It is the machine learning algorithm that learns from labeled data. After the data is analyzed and learned, the algorithm determines which label should be given to new data supplied by the user based on pattern and associating the patterns to the unlabeled new data. Supervised Learning algorithm has two categories i.e Classification & Regression Classification predicts the class or category in which the data belongs to. e.g.: Spam filtering and detection, Churn Prediction, Sentiment Analysis, image classification. Regression predicts a numerical value based on previously observed data. e.g.: House Price Prediction, Stock Price Prediction. Classification Classification is one of the widely and mostly used techniques for determining class the dependent belongs to base on the one or more independent variables. For simple understanding, what classification algorithm does is it simply makes a decision boundary between data po...
Post a Comment
Read more