Machine learningMachine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.
Deep learningDeep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
Tablet computerA tablet computer, commonly shortened to tablet, is a mobile device, typically with a mobile operating system and touchscreen display processing circuitry, and a rechargeable battery in a single, thin and flat package. Tablets, being computers, have similar capabilities, but lack some input/output (I/O) abilities that others have. Modern tablets largely resemble modern smartphones, the only differences being that tablets are relatively larger than smartphones, with screens or larger, measured diagonally, and may not support access to a cellular network.
Convolutional neural networkConvolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.
Neural networkA neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed.
Graphics tabletA graphics tablet (also known as a digitizer, digital graphic tablet, pen tablet, drawing tablet, external drawing pad or digital art board) is a computer input device that enables a user to hand-draw images, animations and graphics, with a special pen-like stylus, similar to the way a person draws images with a pencil and paper. These tablets may also be used to capture data or handwritten signatures. It can also be used to trace an image from a piece of paper that is taped or otherwise secured to the tablet surface.
Optical character recognitionOptical character recognition or optical character reader (OCR) is the electronic or mechanical conversion of s of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene photo (for example the text on signs and billboards in a landscape photo) or from subtitle text superimposed on an image (for example: from a television broadcast).
Long short-term memoryLong short-term memory (LSTM) network is a recurrent neural network (RNN), aimed to deal with the vanishing gradient problem present in traditional RNNs. Its relative insensitivity to gap length is its advantage over other RNNs, hidden Markov models and other sequence learning methods. It aims to provide a short-term memory for RNN that can last thousands of timesteps, thus "long short-term memory".
Recurrent neural networkA recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.
Windows VistaWindows Vista is a major release of the Windows NT operating system developed by Microsoft as the direct successor to Windows XP, which was released in 2001. At the time, this 5-year gap was the longest time span between successive releases of Microsoft's Windows desktop operating systems. Development was finished on November 8, 2006, and over the following three months, it was released in stages to computer hardware and software manufacturers, business customers, and retail channels.
Feedforward neural networkA feedforward neural network (FNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. Its flow is uni-directional, meaning that the information in the model flows in only one direction—forward—from the input nodes, through the hidden nodes (if any) and to the output nodes, without any cycles or loops, in contrast to recurrent neural networks, which have a bi-directional flow.
Stylus (computing)In computing, a stylus (or stylus pen) is a small pen-shaped instrument whose tip position on a computer monitor can be detected. It is used to draw, or make selections by tapping. While devices with touchscreens such as newer computers, mobile devices (smartphones and personal digital assistants), game consoles, and graphics tablets can usually be operated with a fingertip, a stylus provides more accurate and controllable input. The stylus has the same function as a mouse or touchpad as a pointing device; its use is commonly called pen computing.
Windows 7Windows 7 is a major release of the Windows NT operating system developed by Microsoft. It was released to manufacturing on July 22, 2009, and became generally available on October 22, 2009. It is the successor to Windows Vista, released nearly three years earlier. Windows 7's server counterpart, Windows Server 2008 R2, was released at the same time. Windows 7 remained an operating system for use on personal computers, including home and business desktops, laptops, tablet PCs and media center PCs, and itself was replaced in November 2012 by Windows 8, the name spanning more than three years of the product.
Virtual keyboardA virtual keyboard is a software component that allows the input of characters without the need for physical keys. The interaction with the virtual keyboard happens mostly via a touchscreen interface, but can also take place in a different form in virtual or augmented reality. On a desktop computer, a virtual keyboard might provide an alternative input mechanism for users with disabilities who cannot use a conventional keyboard, or for bi- or multi-lingual users who switch frequently between different character sets or alphabets, which may be confusing over time.
TouchscreenA touchscreen or touch screen is the assembly of both an input ('touch panel') and output ('display') device. The touch panel is normally layered on the top of an electronic visual display of an electronic device. The display is often an LCD, AMOLED or OLED display. A user can give input or control the information processing system through simple or multi-touch gestures by touching the screen with a special stylus or one or more fingers. Some touchscreens use ordinary or specially coated gloves to work, while others may only work using a special stylus or pen.
Vanishing gradient problemIn machine learning, the vanishing gradient problem is encountered when training artificial neural networks with gradient-based learning methods and backpropagation. In such methods, during each iteration of training each of the neural networks weights receives an update proportional to the partial derivative of the error function with respect to the current weight. The problem is that in some cases, the gradient will be vanishingly small, effectively preventing the weight from changing its value.
