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.
Neural oscillationNeural oscillations, or brainwaves, are rhythmic or repetitive patterns of neural activity in the central nervous system. Neural tissue can generate oscillatory activity in many ways, driven either by mechanisms within individual neurons or by interactions between neurons. In individual neurons, oscillations can appear either as oscillations in membrane potential or as rhythmic patterns of action potentials, which then produce oscillatory activation of post-synaptic neurons.
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.
Dorsal column–medial lemniscus pathwayThe dorsal column–medial lemniscus pathway (DCML) (also known as the posterior column-medial lemniscus pathway, PCML) is a sensory pathway of the central nervous system that conveys sensations of fine touch, vibration, two-point discrimination, and proprioception (body position) from the skin and joints. It transmits information from the body to the primary somatosensory cortex in the postcentral gyrus of the parietal lobe of the brain.
Neural codingNeural coding (or neural representation) is a neuroscience field concerned with characterising the hypothetical relationship between the stimulus and the individual or ensemble neuronal responses and the relationship among the electrical activity of the neurons in the ensemble. Based on the theory that sensory and other information is represented in the brain by networks of neurons, it is thought that neurons can encode both digital and analog information.
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.
Spinocerebellar tractThe spinocerebellar tract is a nerve tract originating in the spinal cord and terminating in the same side (ipsilateral) of the cerebellum. Proprioceptive information is obtained by Golgi tendon organs and muscle spindles. Golgi tendon organs consist of a fibrous capsule enclosing tendon fascicles and bare nerve endings that respond to tension in the tendon by causing action potentials in type Ib afferents. These fibers are relatively large, myelinated, and quickly conducting.
Somatosensory systemIn physiology, the somatosensory system is the network of neural structures in the brain and body that produce the perception of touch (haptic perception), as well as temperature (thermoception), body position (proprioception), and pain. It is a subset of the sensory nervous system, which also represents visual, auditory, olfactory, and gustatory stimuli. Somatosensation begins when mechano- and thermosensitive structures in the skin or internal organs sense physical stimuli such as pressure on the skin (see mechanotransduction, nociception).
Dorsal column nucleiIn neuroanatomy, the dorsal column nuclei are a pair of nuclei in the dorsal columns in the brainstem. The name refers collectively to the cuneate nucleus and gracile nucleus, which are situated at the lower end of the medulla oblongata. Both nuclei contain second-order neurons of the dorsal column–medial lemniscus pathway, which convey fine touch and proprioceptive information from the body to the brain. The dorsal column nuclei project to the thalamus.
Neural circuitA neural circuit (also known as a biological neural network BNNs) is a population of neurons interconnected by synapses to carry out a specific function when activated. Multiple neural circuits interconnect with one another to form large scale brain networks. Neural circuits have inspired the design of artificial neural networks, though there are significant differences. Early treatments of neural networks can be found in Herbert Spencer's Principles of Psychology, 3rd edition (1872), Theodor Meynert's Psychiatry (1884), William James' Principles of Psychology (1890), and Sigmund Freud's Project for a Scientific Psychology (composed 1895).
Neural decodingNeural decoding is a neuroscience field concerned with the hypothetical reconstruction of sensory and other stimuli from information that has already been encoded and represented in the brain by networks of neurons. Reconstruction refers to the ability of the researcher to predict what sensory stimuli the subject is receiving based purely on neuron action potentials. Therefore, the main goal of neural decoding is to characterize how the electrical activity of neurons elicit activity and responses in the brain.
Primary somatosensory cortexIn neuroanatomy, the primary somatosensory cortex is located in the postcentral gyrus of the brain's parietal lobe, and is part of the somatosensory system. It was initially defined from surface stimulation studies of Wilder Penfield, and parallel surface potential studies of Bard, Woolsey, and Marshall. Although initially defined to be roughly the same as Brodmann areas 3, 1 and 2, more recent work by Kaas has suggested that for homogeny with other sensory fields only area 3 should be referred to as "primary somatosensory cortex", as it receives the bulk of the thalamocortical projections from the sensory input fields.
ProprioceptionProprioception (ˌproʊpri.oʊˈsɛpʃən,_-ə- ), also called kinaesthesia (or kinesthesia), is the sense of self-movement, force, and body position. Proprioception is mediated by proprioceptors, mechanosensory neurons located within muscles, tendons, and joints. Most animals possess multiple subtypes of proprioceptors, which detect distinct kinematic parameters, such as joint position, movement, and load. Although all mobile animals possess proprioceptors, the structure of the sensory organs can vary across species.
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.
Spiking neural networkArtificial neural network Spiking neural networks (SNNs) are artificial neural networks that more closely mimic natural neural networks. In addition to neuronal and synaptic state, SNNs incorporate the concept of time into their operating model. The idea is that neurons in the SNN do not transmit information at each propagation cycle (as it happens with typical multi-layer perceptron networks), but rather transmit information only when a membrane potential—an intrinsic quality of the neuron related to its membrane electrical charge—reaches a specific value, called the threshold.
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.
Trigeminal nerveIn neuroanatomy, the trigeminal nerve (lit. triplet nerve), also known as the fifth cranial nerve, cranial nerve V, or simply CN V, is a cranial nerve responsible for sensation in the face and motor functions such as biting and chewing; it is the most complex of the cranial nerves. Its name (trigeminal, ) derives from each of the two nerves (one on each side of the pons) having three major branches: the ophthalmic nerve (V_1), the maxillary nerve (V_2), and the mandibular nerve (V_3).
Models of neural computationModels of neural computation are attempts to elucidate, in an abstract and mathematical fashion, the core principles that underlie information processing in biological nervous systems, or functional components thereof. This article aims to provide an overview of the most definitive models of neuro-biological computation as well as the tools commonly used to construct and analyze them.
Cerebral cortexThe cerebral cortex, also known as the cerebral mantle, is the outer layer of neural tissue of the cerebrum of the brain in humans and other mammals. The cerebral cortex mostly consists of the six-layered neocortex, with just 10% consisting of allocortex. It is separated into two cortices, by the longitudinal fissure that divides the cerebrum into the left and right cerebral hemispheres. The two hemispheres are joined beneath the cortex by the corpus callosum. The cerebral cortex is the largest site of neural integration in the central nervous system.
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.
