spoken

 Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. 

basically Machine learning focuses on the development of computer programs that can access data and use it learn for themselves.

Currently, machine learning has been used in multiple fields and industries. For example, medical diagnosis, image processing, prediction, classification,  regression etc

Slide 2: 

Machine Learning is categories in 3 parts 

Supervised Learning 

Unsupervised Learning

Reinforecement Learning

Slide 3:

Supervised learning is where you have input variables (x) and an output variable (Y) and you use an algorithm to learn the mapping function from the input to the output.

Y = f(X)

The goal is to approximate the mapping function so well that when you have new input data (x) that you can predict the output variables (Y) for that data.

Basically supervised learning is a learning in which we teach or train the machine using data which is well labeled that means some data is already tagged with the correct answer.

don't say this ## y = e^(b0 + b1*x) / (1 + e^(b0 + b1*x))

Slide 4 Supervised Learning 

Supervised Learning can further be classified into two categories :

• Classification: A classification problem is when the output variable is a category, such as “red” or “blue” or “disease” and “no disease”.
• Regression: A regression problem is when the output variable is a real value, such as “dollars” or “weight”.

Linear Regression for regression problems

Random Forest for classification and regression problems

support vector machine for classification problems 

The majority of practical machine learning uses supervised learning.

Supervised learning is where you have input variables (x) and an output variable (Y) and you use an algorithm to learn the mapping function from the input to the output.

Y = f(X)

The goal is to approximate the mapping function so well that when you have new input data (x) that you can predict the output variables (Y) for that data.

It is called supervised learning because the process of an algorithm learning from the training dataset can be thought of as a teacher supervising the learning process. We know the correct answers, the algorithm iteratively makes predictions on the training data and is corrected by the teacher. Learning stops when the algorithm achieves an acceptable level of performance.

Supervised Learning can further be classified into two categories :

• Classification: A classification problem is when the output variable is a category or it contain discrete value , such as “red” or “blue” or “disease” and “no disease”.
• Regression: A regression problem is when the output variable is a real value or it contain continuous value , such as “dollars” or “weight”.

Slide 5: 

As in the slide we can understand that how supervised perform in thi we have labeled data which we generally called independent variables and lables which we calles dependent variable 

then we feed this data to some supervised model 

after this this model will predict the labels for a unseen data and predict the result 

Slide 6:

Unsupervised learning is where we only have input data (X) and no corresponding output variables.

The goal for unsupervised learning is to model the underlying structure or distribution in the data in order to learn more about the data.

basically Unsupervised learning is the training of machine using information that is neither classified nor labeled and allowing the algorithm to act on that information without guidance

slide 7: 

Unsupervised learning problems can be further grouped into clustering and association problems.

• Clustering: A clustering problem is where you want to discover the inherent groupings in the data, such as grouping customers by purchasing behavior.
• Association:  An association rule learning problem is where you want to discover rules that describe large portions of your data, such as people that buy X also tend to buy Y.

popular examples of unsupervised learning algorithms are:

• k-means for clustering problems.

Slide 8 :

As in this picture we have no labels so we cluster them according to the closest distance fro each other and define the different class for each cluster 

slide 9:

this picture clears out the difference between supervised and unsupervised learning

it showing how supervised treat the data adn unsupervised treat the data 

Slide 10 :

Reinforcement learning is the training of machine learning models to make a sequence of decisions.

and it works on the principle of feedback means it learn from its previous action just like robot 

slide 11 :

The above image shows the robot, diamond, and fire. The goal of the robot is to get the reward that is the diamond and avoid the hurdles that are fire. The robot learns by trying all the possible paths and then choosing the path which gives him the reward with the least hurdles.

 slide 12 :

Deep Learning is a subset of Machine Learning in Artificial Intelligence that can imitate the data processing function of the human brain and create similar patterns the brain used for decision making. 

and it requires large amounts of labeled data.

Examples are :

automated car

Medical Research:  

SLide 13

 It is a structure consisting of ML algorithms wherein the artificial neurons make the core computational unit that focuses on uncovering the underlying patterns or connections within a dataset, just like the human brain does while decision making.

 it is one of the architecture deep learning used 

Slide 14 :

this is the architecture of neural networks where input is our feature and that along with some weights of nwuron feed into hidden layer and predict the result this process is comes under forward propogation 

Slide 15 :

• Neurons – A neuron is a mathematical function designed to imitate the functioning of a biological neuron. 
• Connection and weights –  connections connect a neuron in one layer to another neuron in the same layer or another layer. A weight represents the strength of the connection between the units. The aim is to reduce the weight value to decrease the possibilities of loss (error).
• Propagation function – forward propagation that delivers the “predicted value” and backward propagation that delivers the “error value.”
• Learning rate – Neural Networks are trained using Gradient Descent to optimize the weights. Back-propagation is used at each iteration to calculate the derivative of the loss function in reference to each weight value and subtract it from that weight. Learning rate decides how quickly or slowly you want to update the weight (parameter) values of the model.

slide 15 :

One of the main benefits of deep learning over various machine learning algorithms is its ability to generate new features from limited series of features located in the training dataset. Therefore, deep learning algorithms can create new tasks to solve current ones

The most important difference between deep learning and traditional machine learning is its performance as the scale of data increases. When the data is small, deep learning algorithms don’t perform that well. This is because deep learning algorithms need a large amount of data to understand it perfectly. On the other hand, traditional machine learning algorithms with their handcrafted rules prevail in this scenario. Below image summarizes this fact.

ML required structured data but deep learning networks rely on layers of neural networks