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.
Synaptic plasticityIn neuroscience, synaptic plasticity is the ability of synapses to strengthen or weaken over time, in response to increases or decreases in their activity. Since memories are postulated to be represented by vastly interconnected neural circuits in the brain, synaptic plasticity is one of the important neurochemical foundations of learning and memory (see Hebbian theory). Plastic change often results from the alteration of the number of neurotransmitter receptors located on a synapse.
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.
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.
NeuromodulationNeuromodulation is the physiological process by which a given neuron uses one or more chemicals to regulate diverse populations of neurons. Neuromodulators typically bind to metabotropic, G-protein coupled receptors (GPCRs) to initiate a second messenger signaling cascade that induces a broad, long-lasting signal. This modulation can last for hundreds of milliseconds to several minutes. Some of the effects of neuromodulators include: alter intrinsic firing activity, increase or decrease voltage-dependent currents, alter synaptic efficacy, increase bursting activity and reconfiguration of synaptic connectivity.
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.
Spike-timing-dependent plasticitySpike-timing-dependent plasticity (STDP) is a biological process that adjusts the strength of connections between neurons in the brain. The process adjusts the connection strengths based on the relative timing of a particular neuron's output and input action potentials (or spikes). The STDP process partially explains the activity-dependent development of nervous systems, especially with regard to long-term potentiation and long-term depression.
DopamineDopamine (DA, a contraction of 3,4-dihydroxyphenethylamine) is a neuromodulatory molecule that plays several important roles in cells. It is an organic chemical of the catecholamine and phenethylamine families. Dopamine constitutes about 80% of the catecholamine content in the brain. It is an amine synthesized by removing a carboxyl group from a molecule of its precursor chemical, L-DOPA, which is synthesized in the brain and kidneys. Dopamine is also synthesized in plants and most animals.
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.
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.
Homeostatic plasticityIn neuroscience, homeostatic plasticity refers to the capacity of neurons to regulate their own excitability relative to network activity. The term homeostatic plasticity derives from two opposing concepts: 'homeostatic' (a product of the Greek words for 'same' and 'state' or 'condition') and plasticity (or 'change'), thus homeostatic plasticity means "staying the same through change". Homeostatic synaptic plasticity is a means of maintaining the synaptic basis for learning, respiration, and locomotion, in contrast to the Hebbian plasticity associated with learning and memory.
Dopamine receptorDopamine receptors are a class of G protein-coupled receptors that are prominent in the vertebrate central nervous system (CNS). Dopamine receptors activate different effectors through not only G-protein coupling, but also signaling through different protein (dopamine receptor-interacting proteins) interactions. The neurotransmitter dopamine is the primary endogenous ligand for dopamine receptors. Dopamine receptors are implicated in many neurological processes, including motivational and incentive salience, cognition, memory, learning, and fine motor control, as well as modulation of neuroendocrine signaling.
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.
Chemical synapseChemical synapses are biological junctions through which neurons' signals can be sent to each other and to non-neuronal cells such as those in muscles or glands. Chemical synapses allow neurons to form circuits within the central nervous system. They are crucial to the biological computations that underlie perception and thought. They allow the nervous system to connect to and control other systems of the body. At a chemical synapse, one neuron releases neurotransmitter molecules into a small space (the synaptic cleft) that is adjacent to another neuron.
Monoamine neurotransmitterMonoamine neurotransmitters are neurotransmitters and neuromodulators that contain one amino group connected to an aromatic ring by a two-carbon chain (such as -CH2-CH2-). Examples are dopamine, norepinephrine and serotonin. All monoamines are derived from aromatic amino acids like phenylalanine, tyrosine, and tryptophan by the action of aromatic amino acid decarboxylase enzymes. They are deactivated in the body by the enzymes known as monoamine oxidases which clip off the amine group. Monoaminergic systems, i.
Dopamine agonistA dopamine agonist (DA) is a compound that activates dopamine receptors. There are two families of dopamine receptors, D2-like and D1-like, and they are all G protein-coupled receptors. D1- and D5-receptors belong to the D1-like family and the D2-like family includes D2, D3 and D4 receptors. Dopamine agonists are primarily used in the treatment of Parkinson's disease, and to a lesser extent, in hyperprolactinemia and restless legs syndrome. They are also used off-label in the treatment of clinical depression.
Reward systemThe reward system (the mesocorticolimbic circuit) is a group of neural structures responsible for incentive salience (i.e., "wanting"; desire or craving for a reward and motivation), associative learning (primarily positive reinforcement and classical conditioning), and positively-valenced emotions, particularly ones involving pleasure as a core component (e.g., joy, euphoria and ecstasy). Reward is the attractive and motivational property of a stimulus that induces appetitive behavior, also known as approach behavior, and consummatory behavior.
Brain stimulation rewardBrain stimulation reward (BSR) is a pleasurable phenomenon elicited via direct stimulation of specific brain regions, originally discovered by James Olds and Peter Milner. BSR can serve as a robust operant reinforcer. Targeted stimulation activates the reward system circuitry and establishes response habits similar to those established by natural rewards, such as food and sex. Experiments on BSR soon demonstrated that stimulation of the lateral hypothalamus, along with other regions of the brain associated with natural reward, was both rewarding as well as motivation-inducing.
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.
BrainA brain is an organ that serves as the center of the nervous system in all vertebrate and most invertebrate animals. It is located in the head, usually close to the sensory organs for senses such as vision. It is the most complex organ in a vertebrate's body. In a human, the cerebral cortex contains approximately 14–16 billion neurons, and the estimated number of neurons in the cerebellum is 55–70 billion. Each neuron is connected by synapses to several thousand other neurons.
