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.
ConcertA concert is a live music performance in front of an audience. The performance may be by a single musician, sometimes then called a recital, or by a musical ensemble, such as an orchestra, choir, or band. Concerts are held in a wide variety and size of settings, from private houses and small nightclubs, dedicated concert halls, amphitheatres and parks, to large multipurpose buildings, such as arenas and stadiums. Indoor concerts held in the largest venues are sometimes called arena concerts or amphitheatre concerts.
Music appreciationMusic appreciation is a division of musicology that is designed to teach students how to understand and describe the contexts and creative processes involved in music composition. The concept of music appreciation is often taught as a subset of music theory in higher education and focuses predominantly on Western art music, commonly called "Classical music". This study of music is classified in a number of ways, including (but not limited to) examining music literacy and core musical elements such as pitch, duration, structure, texture and expressive techniques.
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.
Diffusion modelIn machine learning, diffusion models, also known as diffusion probabilistic models or score-based generative models, are a class of latent variable models. They are Markov chains trained using variational inference. The goal of diffusion models is to learn the latent structure of a dataset by modeling the way in which data points diffuse through the latent space. In computer vision, this means that a neural network is trained to denoise images blurred with Gaussian noise by learning to reverse the diffusion process.
Learning to rankLearning to rank or machine-learned ranking (MLR) is the application of machine learning, typically supervised, semi-supervised or reinforcement learning, in the construction of ranking models for information retrieval systems. Training data consists of lists of items with some partial order specified between items in each list. This order is typically induced by giving a numerical or ordinal score or a binary judgment (e.g. "relevant" or "not relevant") for each item.
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.
Musical theatreMusical theatre is a form of theatrical performance that combines songs, spoken dialogue, acting and dance. The story and emotional content of a musical – humor, pathos, love, anger – are communicated through words, music, movement and technical aspects of the entertainment as an integrated whole. Although musical theatre overlaps with other theatrical forms like opera and dance, it may be distinguished by the equal importance given to the music as compared with the dialogue, movement and other elements.
Guitar amplifierA guitar amplifier (or amp) is an electronic device or system that strengthens the electrical signal from a pickup on an electric guitar, bass guitar, or acoustic guitar so that it can produce sound through one or more loudspeakers, which are typically housed in a wooden cabinet. A guitar amplifier may be a standalone wood or metal cabinet that contains only the power amplifier (and preamplifier) circuits, requiring the use of a separate speaker cabinet–or it may be a "combo" amplifier, which contains both the amplifier and one or more speakers in a wooden cabinet.
AutoencoderAn autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data (unsupervised learning). An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation. The autoencoder learns an efficient representation (encoding) for a set of data, typically for dimensionality reduction. Variants exist, aiming to force the learned representations to assume useful properties.
Complex systemA complex system is a system composed of many components which may interact with each other. Examples of complex systems are Earth's global climate, organisms, the human brain, infrastructure such as power grid, transportation or communication systems, complex software and electronic systems, social and economic organizations (like cities), an ecosystem, a living cell, and ultimately the entire universe.
Pop musicPop music is a genre of popular music that originated in its modern form during the mid-1950s in the United States and the United Kingdom. During the 1950s and 1960s, pop music encompassed rock and roll and the youth-oriented styles it influenced. Rock and pop music remained roughly synonymous until the late 1960s, after which pop became associated with music that was more commercial, ephemeral, and accessible.
