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.
Linear predictive codingLinear predictive coding (LPC) is a method used mostly in audio signal processing and speech processing for representing the spectral envelope of a digital signal of speech in compressed form, using the information of a linear predictive model. LPC is the most widely used method in speech coding and speech synthesis. It is a powerful speech analysis technique, and a useful method for encoding good quality speech at a low bit rate.
Google DeepMindDeepMind Technologies Limited, doing business as Google DeepMind, is a British-American artificial intelligence research laboratory which serves as a subsidiary of Google. Founded in the UK in 2010, it was acquired by Google in 2014, becoming a wholly owned subsidiary of Google parent company Alphabet Inc. after Google's corporate restructuring in 2015. The company is based in London, with research centres in Canada, France, and the United States.
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.
AV1AOMedia Video 1 (AV1) is an open, royalty-free video coding format initially designed for video transmissions over the Internet. It was developed as a successor to VP9 by the Alliance for Open Media (AOMedia), a consortium founded in 2015 that includes semiconductor firms, video on demand providers, video content producers, software development companies and web browser vendors. The AV1 bitstream specification includes a reference video codec. In 2018, Facebook conducted testing that approximated real-world conditions, and the AV1 reference encoder achieved 34%, 46.
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.
Joint encodingIn audio engineering, joint encoding refers to a joining of several channels of similar information during encoding in order to obtain higher quality, a smaller file size, or both. The term joint stereo has become prominent as the Internet has allowed for the transfer of relatively low bit rate, acceptable-quality audio with modest Internet access speeds. Joint stereo refers to any number of encoding techniques used for this purpose. Two forms are described here, both of which are implemented in various ways with different codecs, such as MP3, AAC and Ogg Vorbis.
Foundation modelsA foundation model (also called base model) is a large machine learning (ML) model trained on a vast quantity of data at scale (often by self-supervised learning or semi-supervised learning) such that it can be adapted to a wide range of downstream tasks. Foundation models have helped bring about a major transformation in how artificial intelligence (AI) systems are built, such as by powering prominent chatbots and other user-facing AI.
Neural machine translationNeural machine translation (NMT) is an approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model. They require only a fraction of the memory needed by traditional statistical machine translation (SMT) models. Furthermore, unlike conventional translation systems, all parts of the neural translation model are trained jointly (end-to-end) to maximize the translation performance.
