Artificial intelligence

General AI

Machines that possessed the same characteristics of human intelligence. This is the concept we think of as "general AI", which have our senses, all our reason, and think that just like we do.

Neural Networks

An artificial neural network (ANN) is an algorithmic construct that enables machines to learn everything from voice commands and playlist curation to music composition and image recognition. Modeled loosely on the human brain, artificial neural networks enable computers to learn from being fed data

Deep learning

Deep learning is a technique for implementing Machine Learning. Deep learning is an algorithmic approach from the early machine learning crowd, Artificial Neural Networks, came and mostly went over the decades. Neural Networks are inspired by our understanding of the biology of our brains - all those interconnections between the neurons. But, unlike a biological brain where any neuron can connect to any other neuron within a certain physical distance, these artificial neural networks have discrete layers, connections, and directions of data propagation.

Machine learning

Machine Learning is an approach to achieve Artificial Intelligence Machine learning at its most basic is the practice of using algorithms to parse data, learn from it, and then make a determination or prediction about something in the world. So rather than hand-coding software routines with a specific set of instructions to accomplish a particular task, the machine is the trained using larger amounts of data and algorithms that give it the ability to learn how to perform task. Machine learning came directly from minds of the early AI crowd, and the algorithmic approaches over the years included: decision tree, inductive logic programming, cluttering, reinforcement learning, Bayesian networks. As we know, none achieved the ultimate goal of General AI, and even Narrow AI was mostly out of reach with early machine learning approaches.

Transfer Learning

Pre-trained models are extremely useful when they are suitable for the task at hand, but they are often not optimized for the specific dataset users are tackling. As an example, Inception V3 is a model optimized for image classification on a broad set of 1000 categories, but our domain might be dog breed classification. A commonly used technique in deep learning is transfer learning, which adapts a model trained for a similar task to the task at hand. Compared with training a new model from group up, transfer learning requires substantially less data and resources. This is why transfer learning has become the go-to method in many real world use cases, such as cancer detection.

Narrow AI

Technologies that are able to perform specific tasks as well as, or better than, we human can. Examples of narrow AI are things such as image classification on a service like Pinterest and face recognition on Facebook

Feedback loop

With a feedback loop, the system learns continuously by monitoring the effectiveness of predictions and retraining when needed. Monitoring and using the resulting feedback are at the core of machine learning. Just as humans perform a new task, learn from our mistakes, adjust, and act, machine learning is no different.