Unravelling the mysteries of Artificial Intelligence

It is often debated that what makes humans the ultimate intelligent species is the innate quality of doing commonsense reasoning. Humans use common sense knowledge about the world around to take appropriate decisions, and this turns out to be the necessary ingredient for their survival. AI researches have long thought about building commonsense knowledge in AI. They argue that if AI possess necessary commonsense knowledge then it will be a truly intelligent machine. We will discuss two major commonsense projects that exploit this idea: Cyc tries to build a comprehensive ontology and knowledge base of everyday commonsense knowledge. This knowledge can be used by AI applications to do human-like reasoning. Started in 1984, Cyc has come a long way. Today, OpenCyc 4.0 includes the entire Cyc ontology, containing 239,000 concepts and 2,093,000 facts and can be browsed on the OpenCyc website - http://www.cyc.com/platform/opencyc/ . OpenCyc is available for download from Source...

Anomaly detection refers to the problem of finding patterns that do not conform to expected behavior [1]. In the last article "Understanding Neocortex to Create Intelligence" , we explored how applications based on the workings of neocortex create intelligence. Pattern recognition along with prediction makes human brains the ultimate intelligent machines. Prediction help humans to detect anomalies in the environment. Before every action is taken, neocortex predicts the outcome. If there is a deviation from the expected outcome, neocortex detects anomalies, and will take necessary steps to handle them. A system which claims to be intelligent, should have anomaly detection in place. Recent findings using research on neocortex have made it possible to create applications that does anomaly detection. Numenta’s NuPIC using Hierarchical Temporal Memory (HTM) framework is able to do inference and prediction, and hence anomaly detection. HTM accurately predicts anomalies in real...

There are two approaches to create intelligence in machines. One is to understand how human brain creates intelligence and replicate the methods used by it to create AI. The other is to take a fresh engineering approach to create intelligence. There is an ongoing debate as to which approach is feasible or better. Few companies like Numenta and Vicarious have invested in understanding the neocortex. They have launched successful applications that work on the principles of neocortex. Other big companies including Google, Microsoft and Facebook use deep learning to create applications that can do major classification tasks. But deep learning does not exploit the concepts of neocortex, and hence is not up to the mark to do continuous learning. The deep learning models first go through a training phase and then the models are used to do classification. The idea that makes neocortex truly intelligent is that it is able to do pattern matching and prediction. This has given humans the ...

There is a growing consensus that the brain uses Bayesian to perform cognition. Our brain is capable of learning using only positive examples, unlike the approach taken in machine learning where there is a need to provide both positive and negative examples. Consider an example where a parent says to a child “Look at that dog!” A child is capable of categorizing all future dogs it looks at from only one or two examples. The brain of that child is generalizing using some form of Bayesian inference. Welcome to the world of One Shot Learning. The discovery that Bayes himself abandoned for unknown reasons, today stands at the forefront of making Artificial Intelligence a reality. Learning from few examples is what we are good at, and any intelligent machine is expected to do. Thanks to Pierre Simon Laplace who rediscovered it and gave Bayes' theorem a mathematical form, cognitive AI research uses Bayesian to make machines learn.         ...

The day AI reads a document and answers each and every question asked and do reasoning on it, will be the day when we will call it true intelligence. Welcome to the world of Information Extraction, where algorithms try to extract information from unstructured documents into structured information, which the AI can further access to answer questions. Apparently easy for humans perform such an important task, looks hard for AI to do. The difficulty lies in recognizing named entities, identifying context, relationship extraction, understanding tables and diagrams, and many more. The research in Information Extraction has progressed exponentially since this problem was identified, and today we have lot of open source tools at our disposal. Any toolkit for Information Extraction is expected to contain the following modules Tokenizer - Converts a sequence of characters into a sequence of tokens Gazetteers - Entity dictionaries used as a lookup table Sentence splitter - Under...

Machine Learning algorithms require tens and thousands of CPU based servers to train a model, which turns out to be an expensive activity. Machine Learning researchers and engineers are often faced with the problem of running their algorithms fast. Although initially invented for processing graphics in computer games, GPUs today are used in machine learning to perform feature detection from vast amount of unlabeled data. Compared to CPUs, GPUs take far less time to train models that perform classification and prediction. Characteristics of GPUs that make them ideal for machine learning Handle large datasets Needs far less data centre infrastructure Can be specialized for specific machine learning needs Perform vector computations faster than any known processor Designed to perform data parallel computation NVIDIA CUDA GPUs today are used to build deep learning image processing tools for  Adobe Creative Cloud. According to NVIDIA blog future Adobe appli...

Widely used in image recognition, Convolutional Neural Networks (CNNs) consist of multiple layers of neuron collection which look at small window of the input image, called receptive fields. The history of Convolutional Neural Networks begins with a famous experiment “Receptive Fields of Single Neurons in the Cat’s Striate Cortex” conducted by Hubel and Wiesel. The experiment confirmed the long belief of neurobiologists and psychologists that the neurons in the brain act as feature detectors. The first neural network model that drew inspiration from the hierarchy model of the visual nervous system proposed by Hubel and Wiesel was Neocognitron invented by Kunihiko Fukushima, and had the ability of performing unsupervised learning. Kunihiko Fukushima’s approach was commendable as it was the first neural network model having the capability of pattern recognition similar to human brain. The model gave a lot of insight and helped future understanding of the brain. A successful ad...