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.
Single instruction, multiple dataSingle instruction, multiple data (SIMD) is a type of parallel processing in Flynn's taxonomy. SIMD can be internal (part of the hardware design) and it can be directly accessible through an instruction set architecture (ISA), but it should not be confused with an ISA. SIMD describes computers with multiple processing elements that perform the same operation on multiple data points simultaneously. Such machines exploit data level parallelism, but not concurrency: there are simultaneous (parallel) computations, but each unit performs the exact same instruction at any given moment (just with different data).
Vanishing gradient problemIn machine learning, the vanishing gradient problem is encountered when training artificial neural networks with gradient-based learning methods and backpropagation. In such methods, during each iteration of training each of the neural networks weights receives an update proportional to the partial derivative of the error function with respect to the current weight. The problem is that in some cases, the gradient will be vanishingly small, effectively preventing the weight from changing its value.
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.
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.
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.
Feedforward neural networkA feedforward neural network (FNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. Its flow is uni-directional, meaning that the information in the model flows in only one direction—forward—from the input nodes, through the hidden nodes (if any) and to the output nodes, without any cycles or loops, in contrast to recurrent neural networks, which have a bi-directional flow.
Long short-term memoryLong short-term memory (LSTM) network is a recurrent neural network (RNN), aimed to deal with the vanishing gradient problem present in traditional RNNs. Its relative insensitivity to gap length is its advantage over other RNNs, hidden Markov models and other sequence learning methods. It aims to provide a short-term memory for RNN that can last thousands of timesteps, thus "long short-term memory".
BackpropagationAs a machine-learning algorithm, backpropagation performs a backward pass to adjust the model's parameters, aiming to minimize the mean squared error (MSE). In a single-layered network, backpropagation uses the following steps: Traverse through the network from the input to the output by computing the hidden layers' output and the output layer. (the feedforward step) In the output layer, calculate the derivative of the cost function with respect to the input and the hidden layers.
Multiple instruction, multiple dataIn computing, multiple instruction, multiple data (MIMD) is a technique employed to achieve parallelism. Machines using MIMD have a number of processors that function asynchronously and independently. At any time, different processors may be executing different instructions on different pieces of data. MIMD architectures may be used in a number of application areas such as computer-aided design/computer-aided manufacturing, simulation, modeling, and as communication switches.
Single instruction, multiple threadsSingle instruction, multiple threads (SIMT) is an execution model used in parallel computing where single instruction, multiple data (SIMD) is combined with multithreading. It is different from SPMD in that all instructions in all "threads" are executed in lock-step. The SIMT execution model has been implemented on several GPUs and is relevant for general-purpose computing on graphics processing units (GPGPU), e.g. some supercomputers combine CPUs with GPUs. The processors, say a number p of them, seem to execute many more than p tasks.
Stream processingIn computer science, stream processing (also known as event stream processing, data stream processing, or distributed stream processing) is a programming paradigm which views streams, or sequences of events in time, as the central input and output objects of computation. Stream processing encompasses dataflow programming, reactive programming, and distributed data processing. Stream processing systems aim to expose parallel processing for data streams and rely on streaming algorithms for efficient implementation.
Batch normalizationBatch normalization (also known as batch norm) is a method used to make training of artificial neural networks faster and more stable through normalization of the layers' inputs by re-centering and re-scaling. It was proposed by Sergey Ioffe and Christian Szegedy in 2015. While the effect of batch normalization is evident, the reasons behind its effectiveness remain under discussion. It was believed that it can mitigate the problem of internal covariate shift, where parameter initialization and changes in the distribution of the inputs of each layer affect the learning rate of the network.
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.
Complex instruction set computerA complex instruction set computer (CISC ˈsɪsk) is a computer architecture in which single instructions can execute several low-level operations (such as a load from memory, an arithmetic operation, and a memory store) or are capable of multi-step operations or addressing modes within single instructions. The term was retroactively coined in contrast to reduced instruction set computer (RISC) and has therefore become something of an umbrella term for everything that is not RISC, where the typical differentiating characteristic is that most RISC designs use uniform instruction length for almost all instructions, and employ strictly separate load and store instructions.
One-instruction set computerA one-instruction set computer (OISC), sometimes referred to as an ultimate reduced instruction set computer (URISC), is an abstract machine that uses only one instruction - obviating the need for a machine language opcode. With a judicious choice for the single instruction and given infinite resources, an OISC is capable of being a universal computer in the same manner as traditional computers that have multiple instructions. OISCs have been recommended as aids in teaching computer architecture and have been used as computational models in structural computing research.
Instruction set architectureIn computer science, an instruction set architecture (ISA), also called computer architecture, is an abstract model of a computer. A device that executes instructions described by that ISA, such as a central processing unit (CPU), is called an implementation. In general, an ISA defines the supported instructions, data types, registers, the hardware support for managing main memory, fundamental features (such as the memory consistency, addressing modes, virtual memory), and the input/output model of a family of implementations of the ISA.
Instruction pipeliningIn computer engineering, instruction pipelining is a technique for implementing instruction-level parallelism within a single processor. Pipelining attempts to keep every part of the processor busy with some instruction by dividing incoming instructions into a series of sequential steps (the eponymous "pipeline") performed by different processor units with different parts of instructions processed in parallel. In a pipelined computer, instructions flow through the central processing unit (CPU) in stages.
Heterogeneous System ArchitectureHeterogeneous System Architecture (HSA) is a cross-vendor set of specifications that allow for the integration of central processing units and graphics processors on the same bus, with shared memory and tasks. The HSA is being developed by the HSA Foundation, which includes (among many others) AMD and ARM. The platform's stated aim is to reduce communication latency between CPUs, GPUs and other compute devices, and make these various devices more compatible from a programmer's perspective, relieving the programmer of the task of planning the moving of data between devices' disjoint memories (as must currently be done with OpenCL or CUDA).
Reduced instruction set computerIn computer engineering, a reduced instruction set computer (RISC) is a computer architecture designed to simplify the individual instructions given to the computer to accomplish tasks. Compared to the instructions given to a complex instruction set computer (CISC), a RISC computer might require more instructions (more code) in order to accomplish a task because the individual instructions are written in simpler code.
