Critics of recent advances in artificial intelligence complain that although these advances have produced remarkable improvements in AI systems, these systems still do not exhibit ‘real’, ‘true’, or ‘genuine’ understanding. The use of words like ‘real’, ‘true’, and ‘genuine’ imply that ‘understanding’ is binary. A system either exhibits ‘genuine’ understanding or it does not. The difficulty with this way of thinking is that human understanding is never complete and perfect. In this article, I argue that ‘understanding’ exists along a continuous spectrum of capabilities. Consider, for example, the concept of ‘water’. Most people understand many properties of water: it is wet, you can drink it, plants need it, it forms ice if chilled, and so on. But unfortunately, many people do not understand that water is an electrical conductor and, therefore, one should not use a blowdryer in the shower. Nonetheless, we do not say of those people that they lack ‘real’, ‘true’, or ‘genuine’ understanding of ‘water’. Instead, we say that their understanding is incomplete.

Six AI priorities you can’t afford to ignore:
1. Structure: Organize for ROI and momentum
2. Workforce: Teach AI citizens and specialists to work together
3. Trust: Make AI responsible in all its dimensions
4. Data: Locate and label to teach the machines
5. Reinvention: Monetize AI through personalization and higher quality
6. Convergence: Combine AI with analytics, the IoT and more

In this digital world ‘encoding’ is a powerful word, with its application and presence spread in all aspect. In general, Encoding is the process of converting data from one form to another required form. One of the best examples of encoding comes from the era before the outbreak of internet, Use of Morse code which was character encoding scheme that encodes text characters as standardized sequences of two different signal durations called dots and dashes or dits and dashes. The World of Data also makes use of encoding for encryption, telecommunication of data, etc. For Machine to understand the trends and vicinity of data, it is necessary that the data be numerical. Almost all ML algorithm requires data in numerical form. In this story, we’ll go through the encoding methods that are necessary for the machine to interpret the data(more specifically categorical data) and learn from it.

So that our machine learning models can tell the difference between 1 / 2 and 50 / 100.

Everything you need to know about preventing data leakage when building a machine learning model.

1. Establish a Baseline at the onset
2. Continuous Integration is the Way Forward
3. Your model might break into Production
4. Your model might not even go to Production
5. Maintainance and Feedback Loop

A recurrent neural network (RNN) is a variation of a basic neural network. RNNs are good for processing sequential data such as natural language processing and audio recognition. They had, until recently, suffered from short-term-memory problems. In this post I will try explaining what an (1) RNN is, (2) the vanishing gradient problem, and (3) the solutions to this problem known as long-short-term-memory (LSTM)and gated recurrent units(GRU).

Markov Chains and Markov Models made EASY.