3 W’s of Machine Learning: What, Where, When?

Original article was published on Deep Learning on Medium

3 W’s of Machine Learning: What, Where, When?

I. What is Machine Learning?

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

ML is sub part of AI.

The process of learning begins with observations or data, such as examples, direct experience, or instruction, in order to look for patterns in data and make better decisions in the future based on the examples that we provide. The primary aim is to allow the computers learn automatically without human intervention or assistance and adjust actions accordingly.

Are Machines and Humans are related?In the current era of technology machines are acting and standing parallel of humans. Humans have been learning from their past experiences and acts accordingly to the future situations. But, if machines can think, feel, act and start learning by themselves? This looks fascinating, but always remember we are living in the era of machines. In no less time humans would be replaced through these machines. Well, though it has started to happen.

Robot Hugging a Girl.

How does Machine learn and work?The term coined after this is Machine Learning. The Machine Learning algorithm is trained using training data set to create a model. When a new input data is introduced to the ML algorithm, it makes a prediction on the basis of the model.

The Machine Learning algorithm is deployed after considering the prediction accuracy and if it fails the accuracy it can’t be deployed for human use.

Process in Machine Learning algorithm.

Machine Learning Algorithm.

Types of Machine Learning-The learning is divided into four categories.

  1. Supervised Machine Learning-”Teach me”.
  2. Unsupervised Machine Learning-”I am able to learn”.
  3. Semi-supervised Machine Learning-”Between supervised and unsupervised learning”.
  4. Reinforcement Machine Learning-”Hit and Trial”
  • Supervised machine learning algorithms can apply what has been learned in the past to new data using labeled examples to predict future events. Starting from the analysis of a known training dataset, the learning algorithm produces an inferred function to make predictions about the output values. The system is able to provide targets for any new input after sufficient training. The learning algorithm can also compare its output with the correct, intended output and find errors in order to modify the model accordingly.
  • In contrast, unsupervised machine learning algorithms are used when the information used to train is neither classified nor labeled. Unsupervised learning studies how systems can infer a function to describe a hidden structure from unlabeled data. The system doesn’t figure out the right output, but it explores the data and can draw inferences from datasets to describe hidden structures from unlabeled data.
  • Semi-supervised machine learning algorithms fall somewhere in between supervised and unsupervised learning, since they use both labeled and unlabeled data for training — typically a small amount of labeled data and a large amount of unlabeled data. The systems that use this method are able to considerably improve learning accuracy. Usually, semi-supervised learning is chosen when the acquired labeled data requires skilled and relevant resources in order to train it / learn from it. Otherwise, acquiring unlabeled data generally doesn’t require additional resources.
  • Reinforcement machine learning algorithms is a learning method that interacts with its environment by producing actions and discovers errors or rewards. Trial and error search and delayed reward are the most relevant characteristics of reinforcement learning. This method allows machines and software agents to automatically determine the ideal behavior within a specific context in order to maximize its performance. Simple reward feedback is required for the agent to learn which action is best; this is known as the reinforcement signal.

II. Where Can You Find Machine Learning?Machine Learning is found every where in the today’s era. It lies within our mobile phones and the applications we use. Whenever we shop online through e-commerce websites we get some or the other predictions about items it’s completely based on the Machine Learning as it is able to make recommendation on the basis of our past shopping details or the items we have viewed earlier. The Music application recommend the songs on the basis of on the songs we have enjoyed listening in the past. The face recognition in our mobile phones and that of Facebook and many others. Machine Learning is spreading at a very fast pace in the Medical Science too. It is helping the doctors to diagnose the patients and the online pharmacy to sell medicines. I could list as many I can this is why Machine Learning is one of the most interesting field to explore.

III. When Can We Use Machine Learning?Well, Machine Learning is used when we are limited to the structured data. This algorithm learning technique fits best is such cases. And works unimaginable when their is a large amount of data. It can be used when we want to make judgments based on images, videos and text recognition predictions. It can be used where ever their is a human need.