Reinforcement learningReinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning differs from supervised learning in not needing labelled input/output pairs to be presented, and in not needing sub-optimal actions to be explicitly corrected.
Deep reinforcement learningDeep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.
Q-learningQ-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic transitions and rewards without requiring adaptations. For any finite Markov decision process (FMDP), Q-learning finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all successive steps, starting from the current state.
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.
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.
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.
Artificial neural networkArtificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.
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.
Types of artificial neural networksThere are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.
Residual neural networkA Residual Neural Network (a.k.a. Residual Network, ResNet) is a deep learning model in which the weight layers learn residual functions with reference to the layer inputs. A Residual Network is a network with skip connections that perform identity mappings, merged with the layer outputs by addition. It behaves like a Highway Network whose gates are opened through strongly positive bias weights. This enables deep learning models with tens or hundreds of layers to train easily and approach better accuracy when going deeper.
Force TouchForce Touch is a haptic technology developed by Apple Inc. that enables trackpads and touchscreens to distinguish between various levels of force being applied to their surfaces. It uses pressure sensors to add another method of input to Apple's devices. The technology was first unveiled on September 9, 2014, during the introduction of Apple Watch. Starting with the Apple Watch, Force Touch has been incorporated into many products within Apple's lineup. This notably includes MacBooks and the Magic Trackpad 2.
Electronic musical instrumentAn electronic musical instrument or electrophone is a musical instrument that produces sound using electronic circuitry. Such an instrument sounds by outputting an electrical, electronic or digital audio signal that ultimately is plugged into a power amplifier which drives a loudspeaker, creating the sound heard by the performer and listener. An electronic instrument might include a user interface for controlling its sound, often by adjusting the pitch, frequency, or duration of each note.
Musical instrumentA musical instrument is a device created or adapted to make musical sounds. In principle, any object that produces sound can be considered a musical instrument—it is through purpose that the object becomes a musical instrument. A person who plays a musical instrument is known as an instrumentalist. The history of musical instruments dates to the beginnings of human culture. Early musical instruments may have been used for rituals, such as a horn to signal success on the hunt, or a drum in a religious ceremony.
Rectifier (neural networks)In the context of artificial neural networks, the rectifier or ReLU (rectified linear unit) activation function is an activation function defined as the positive part of its argument: where x is the input to a neuron. This is also known as a ramp function and is analogous to half-wave rectification in electrical engineering. This activation function was introduced by Kunihiko Fukushima in 1969 in the context of visual feature extraction in hierarchical neural networks.
Feature learningIn machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process.
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.
Multi-touchIn computing, multi-touch is technology that enables a surface (a touchpad or touchscreen) to recognize the presence of more than one point of contact with the surface at the same time. The origins of multitouch began at CERN, MIT, University of Toronto, Carnegie Mellon University and Bell Labs in the 1970s. CERN started using multi-touch screens as early as 1976 for the controls of the Super Proton Synchrotron. Capacitive multi-touch displays were popularized by Apple's iPhone in 2007.
Sampler (musical instrument)A sampler is an electronic musical instrument that records and plays back samples (portions of sound recordings). Samples may comprise elements such as rhythm, melody, speech, sound effects or longer portions of music. The mid-20th century saw the introduction of keyboard instruments that played sounds recorded on tape, such as the Mellotron. As technology improved, cheaper standalone samplers with more memory emerged, such as the E-mu Emulator, Akai S950 and Akai MPC. Samples may be loaded or recorded by the user or by a manufacturer.
Experimental musical instrumentAn experimental musical instrument (or custom-made instrument) is a musical instrument that modifies or extends an existing instrument or class of instruments, or defines or creates a new class of instrument. Some are created through simple modifications, such as cracked drum cymbals or metal objects inserted between piano strings in a prepared piano. Some experimental instruments are created from household items like a homemade mute for brass instruments such as bathtub plugs.
Keyboard instrumentA keyboard instrument is a musical instrument played using a keyboard, a row of levers that are pressed by the fingers. The most common of these are the piano, organ, and various electronic keyboards, including synthesizers and digital pianos. Other keyboard instruments include celestas, which are struck idiophones operated by a keyboard, and carillons, which are usually housed in bell towers or belfries of churches or municipal buildings. Today, the term keyboard often refers to keyboard-style synthesizers.
