Introduction to Machine Learning

• Machine learning is the science and art of programming computers so they can learn from data.
• "Machine Learning" is the field of study that gives computers the ability to learn without being explicitly programmed.
• A computer program learns from experience E with respect to some task T and a performance measure P, if its performance on T, as measured by P, improves with experience E.

Why Use Machine Learning?

• Machine Learning simplifies solutions that require a lot of hand-tuning or long lists of rules.
• One Machine Learning algorithm can often simplify code and perform better.
• Machine learning aids in complex problems for which there is no good solution using a traditional approach.
• The best machine learning techniques can find a solution.
• A Machine Learning system can adapt to new data in fluctuating environments
• Machine learning helps to get insights about complex problems and large amounts of data.

Types of Machine Learning Systems

• There are many different types of Machine Learning systems, making it useful to classify them in broad categories
• Machine learning systems are based on whether they are trained with human supervision.
• Supervised, unsupervised, semi-supervised, and reinforcement learning are classifications
• They are classified upon whether they can learn incrementally on the fly (online vs batch learning).
• They are classified based on if they work by simply comparing new data points to known data points or detect patterns to build a predictive model.
• Instance-based versus model-based learning are classifications

Supervised Learning

• The training data includes the desired solutions.
• A typical task is classification.
• A spam filter is trained with many example emails along with their class (spam or ham), and must learn how to classify new emails.
• Another typical task is to predict a target numeric value, such as the price of a car, given a set of features (mileage, age, brand, etc.) called predictors.
• This sort of task is called regression

Supervised Learning Important Algorithms

• k-Nearest Neighbors
• Linear Regression
• Logistic Regression
• Support Vector Machines (SVMs)
• Decision Trees and Random Forests
• Neural networks

Unsupervised Learning

• The training data is unlabeled.

Unsupervised Learning Important Algorithms

• Clustering
• K-Means
• DBSCAN
• Hierarchical Cluster Analysis (HCA)
• Anomaly detection and novelty detection and includes the algorithms:
• One-class SVM
• Isolation Forest

Semi-Supervised Learning

• Some algorithms can deal with partially labeled training data, usually with a lot of unlabeled data and a little bit of labeled data.

Reinforcement Learning

• The learning system is called an agent.
• The agent can observe the environment, select and perform actions, and get rewards in return (or penalties in the form if negative rewards).
• The agent learns what the best strategy is, called a policy, to get the most reward over time.
• A policy defines what action the agent should choose when it is in a given situation.

Batch and Online Learning

• Machine Learning systems can be classified based on whether or not the system can learn incrementally from a stream of incoming data.

Batch Learning

• The system is incapable of learning incrementally.
• Batch learning must be trained using all the available data, generally taking a lot of time and computing resources.
• It is typically done offline.
• The system is trained, launched into production, and runs without learning anymore; it just applies what it has learned.
• This is called offline learning.

Online Learning

• You train the system incrementally by feeding it data instances sequentially, either individually or by small groups called mini-batches.
• Each learning step is fast and cheap, so the system can learn about new data on the fly, as it arrives.

Instance Based vs Model Based Learning

• One way to categorize Machine Learning systems is by how they generalize.
• Most Machine Learning tasks are about making predictions.
• Given instance-based training examples, the system needs to be able to generalize to examples it has never seen before.
• Having a good performance measure on the training data is good, but insufficient; the true goal is to perform well on new instances.
• Two main approaches to generalization: instance-based learning and model based learning.

Instance Based Learning

• The system learns the examples by heart.
• System then generalizes to new cases by comparing them to the learned examples (or a subset of them) using a similarity measure.

Model Based Learning

• Generalizes from a set of examples by building a model.
• Then uses that model to make predictions.

Main Challenges of Machine Learning

• Selecting a learning algorithm and training it on some data.
• Two things that can go wrong are “bad algorithm” and “bad data”.
• The challenges include:
• Insufficient Quantity of Training Data
• Nonrepresentative Training Data
• Poor Quality Data
• Irrelevant Features
• Overfitting the Training Data
• Underfitting the Training Data
• Stepping Back
• Testing and Validating