Diptendu is an I.T engineer, Passionate about Computers and love to share his knowledge and experience.
What is Machine Learning?
Have you ever wondered, How YouTube knows the next video you wanted to play and recommend it? How online Music Streaming Apps know which song do you like?
Well, all these are possible due to Machine Learning.
Machine learning is the semi-automated extraction of knowledge from data.
In simple terms Machine Learning is a type of computer science that allows computer programs to learn and improve all on their own. With the ML a machine can gain knowledge based on their experiences. Applications learn from previous computations and use algorithms and patterns to produce desired results.
In traditional programming your code compiles into a binary that is typically called a program. In machine learning, the item you create from the data and label are called a model.
Machine Learning is a subset of Artificial Intelligence. It feeds on Training data which makes the Machine intelligent.
Where Machine Learning is used?
Machine Learning is used in various fields like:-
- Speech recognition- A voice model is trained which fetch desired words from it.
- Content Recommendation: Used in various Online platforms such as YouTube,Netflix,Spotify,etc
- Auto Driving Cars- it detects the obstacles and move accordingly to avoid collision
- Image recognition - It process the image pattern and and guess the object. Example- Google lens
- Handwriting to text
- Future Stock Market prediction
- Facial Expression Recognition
- Navigating on outer space or planets
- Keyboard Word Suggestions
- Maps and Navigation
- Computational Biology
- Google Search Engine
How Machine learning enables auto driving
How Machine Learning works?
Machine Learning has four phases : Pre-processing, Learning, Evaluation and Prediction
These phases are generally known as Machine Learning Algorithm.
There are 5 steps, generally, in all machine learning algorithms:
1. You input the data that needs to go into the algorithm
2. The algorithm analyzes the input data and finds patterns
3. The algorithm makes a prediction or a decision by on the patterns or the analysis
4. The algorithm learns from the feedback to make the decisions better next time
5. Repeat everything again
More the data more accurate the results.
Machine Learning are categorized into Supervised Learning, Unsupervised Learning, Semi-Supervised Learning and Reinforcement Learning.
- Supervised Learning- Making prediction using data. It is the simple form where the Data is Labeled.The human experts act as the teacher where we feed the computer with training data containing the input predictors, and we show it the correct answers (output) and from the data the computer should be able to learn the patterns.
- Unsupervised Learning- Extracting structure from data. Here the data is not labeled but it identifies by its features and statistic. There is no teacher at all, actually the computer might be able to teach you new things after it learns patterns in data, these algorithms a particularly useful in cases where the human expert doesn’t know what to look for in the data.
- Semi-Supervised Learning- It has training data with few desired outputs.These methods exploit the idea that even though the group memberships of the unlabeled data are unknown, this data carries important information about the group parameters.
- Reinforcement Learning- it basically works on feedback system, where machine give the output from the algorithms and when the feedback is given whether it is right or wrong machine learn accordingly. Reinforcement learning algorithm (called the agent) continuously learns from the environment in an iterative fashion. In the process, the agent learns from its experiences of the environment until it explores the full range of possible states.
Machine Learning Algorithms
Every ML algorithms has three components:-
- Representation - this describes how you want to look at your data. Sometimes, you may want to think of your data in terms of individuals
- Evaluation - for supervised learning purposes, you’ll need to evaluate or put a score on how well your learner is doing so it can improve. This evaluation is done using an evaluation function
- Optimization - using the evaluation function from above, you need to find the learner with the best score from this evaluation function using a choice of optimization technique. Examples are a greedy search and gradient descent.
Skills needed before Machine Learning
I truly believe that you can learn everything if you are passionate about it.
Machine Learning requires the knowledge of any programming language such as (Python, Java, R, Ruby, etc)
Mathematics pays a very significant role in Machine Learning algorithms. Mathematical topics include - Linear Algebra, Probability Theory and Statistics, Discrete Mathematics, Multivariate Calculus, etc
Some of the common algorithms are :
- The Nearest Neighbor
- Naive Bayes
- Decision Trees
- Linear Regression
- Support Vector Machines (SVM)
- Neural Networks
- k-means clustering, Association Rules
- Temporal Difference (TD)
- Deep Adversarial Networks
Future scope of Machine Learning
Technology is evolving day by day.We are yet to discover all the possibilities of Machine Learning. In future we might see some more amazing applications of ML.
The Era has already began, making our lifestyles more easier and convenient. In this revolution there will be a lots of job opportunities for Machine Learning and Artificial Intelligence. So start exploring the world of possibilities with Machine Learning.
This content is accurate and true to the best of the author’s knowledge and is not meant to substitute for formal and individualized advice from a qualified professional.
© 2020 Diptendu Biswas
Tania on April 23, 2020:
Thankyou for sharing ur knowledge!!!
Diptendu Biswas (author) from India on April 23, 2020:
Nandini ghosh on April 23, 2020:
Thanks for the basic idea
Nandini on April 23, 2020:
It was so informative.