why we use machine learning?

  What Is Machine Learning? 

 Machine learning is the science (and art) of programming computers so they can learn from data.

Use Machine Why Learning?

 Problems for which existing solutions require a lot of fine-tuning or long lists of rules (a machine learning model can often simplify code and perform better than the traditional approach) .

 • Complex problems for which using a traditional approach yields no good solution (the best machine learning techniques can perhaps find a solution) .

 • Fluctuating environments (a machine learning system can easily be retrained on new data, always keeping it up to date). 

 • Getting insights about complex problems and large amounts of data.

 Machine Learning in our Projects

 • Segment customers and find the best marketing strategy for each group. •

 • Recommend products for each client based on what similar clients bought. •

 • Detect which transactions are likely to be fraudulent. •

 • Forecast next year’s revenue.

 Objective and Approach

 The concepts, tools, and intuition you need to implement programs capable of learning from data. For this we will be using production-ready Python frameworks:

 • Scikit-Learn is very easy to use, yet it implements many machine learning algorithms efficiently, so it makes for a great entry point to learning machine learning.

• TensorFlow is a more complex library for distributed numerical computation. It makes it possible to train and run very large neural networks efficiently by dis tributing the computations across potentially hundreds of multi-GPU (graphics processing unit) servers. TensorFlow (TF) was created at Google and supports many of its large-scale machine learning applications. 

•  Keras  is a high-level deep learning API that makes it very simple to train and run neural networks. Keras comes bundled with TensorFlow, and it relies on TensorFlow for all the intensive computations.

 Part I, “The Fundamentals of Machine Learning”, covers the following topics: 

 • What machine learning is, what problems it tries to solve, and the main categories and fundamental concepts of its systems •.

 • The steps in a typical machine learning project.

 • Learning by fitting a model to data.

 • Optimizing a cost function.

 • Handling, cleaning, and preparing data .

 • Selecting and engineering features. 

 • Selecting a model and tuning hyperparameters using cross-validation .

 • The challenges of machine learning, in particular underfitting and overfitting (the bias/variance trade-off) .

 • The most common learning algorithms: linear and polynomial regression, logistic regression, k-nearest neighbors, support vector machines, decision trees, random forests, and ensemble methods .

 • Reducing the dimensionality of the training data to fight the “curse of dimensionality” . 

 • Other unsupervised learning techniques, including clustering, density estimation, and anomaly. detection

 Part II, “Neural Networks and Deep Learning”, covers the following topics:  

 • What neural nets are and what they’re good for 

 • Building and training neural nets using TensorFlow and Keras.

 • The most important neural net architectures: feedforward neural nets for tabular data, convolutional nets for computer vision, recurrent nets and long short-term memory (LSTM) nets for sequence processing, encoder–decoders and trans formers for natural language processing (and more!), autoencoders, generative adversarial networks (GANs), and diffusion models for generative learning.

 • Techniques for training deep neural nets.

 • How to build an agent (e.g., a bot in a game) that can learn good strategies through trial and error, using reinforcement learning. 

 • Loading and preprocessing large amounts of data efficiently.

 • Training and deploying TensorFlow models at scale.

TYPES OF MACHINE LEARNING

1)Supervised      2)Unsupervised         3)Semi-supervised           4)Reinforcement

Supervised learning:- It generates a mathematical relationship between i/p and o/p.

also predict of new i/p

It consists of two types:-

1)Regression- provides o/p in numerical form

2)classification-provide o/p in categorical form

Unsupervised learning:- it consists only i/p

It consists of four types:-

1)Clustering

2)Dimensionally reduction

3)Anomaly detection

4)Association

Semi-supervised:-Partially supervised and partially unsupervised.& no i/p and o/p data:

Reinforcement:-Technique that trains  software to make decision to achieve the most optimal result. 

    •continue more interesting topic related to this topic in next posts

thankyou   😊