Random Backpropagation Research Articles

Trajectory Analysis of 6-DOF Industrial Robot Manipulators by Using Artificial Neural Networks.

Robot manipulators are robotic systems that are frequently used in automation systems and able to provide increased speed, precision, and efficiency in the industrial applications. Due to their nonlinear and complex nature, it is crucial to optimize the robot manipulator systems in terms of trajectory control. In this study, positioning analyses based on artificial neural networks (ANNs) were performed for robot manipulator systems used in the textile industry, and the optimal ANN model for the high-accuracy positioning was improved. The inverse kinematic analyses of a 6-degree-of-freedom (DOF) industrial denim robot manipulator were carried out via four different learning algorithms, delta-bar-delta (DBD), online back propagation (OBP), quick back propagation (QBP), and random back propagation (RBP), for the proposed neural network predictor. From the results obtained, it was observed that the QBP-based 3-10-6 type ANN structure produced the optimal results in terms of estimation and modeling of trajectory control. In addition, the 3-5-6 type ANN structure was also improved, and its root mean square error (RMSE) and statistical R2 performances were compared with that of the 3-10-6 ANN structure. Consequently, it can be concluded that the proposed neural predictors can successfully be employed in real-time industrial applications for robot manipulator trajectory analysis.

Scalable Nanophotonic-Electronic Spiking Neural Networks

Spiking neural networks (SNN) provide a new computational paradigm capable of highly parallelized, real-time processing. Photonic devices are ideal for the design of high-bandwidth, parallel architectures matching the SNN computational paradigm. Furthermore, the co-integration of CMOS and photonic elements combineslow-loss photonic devices with analog electronics for greater flexibility of nonlinear computational elements. We designed and simulated an optoelectronic spiking neuron circuit on a monolithic silicon photonics (SiPh) process that replicates useful spiking behaviors beyond the leaky integrate-and-fire (LIF). Additionally, we explored two learning algorithms with the potential for on-chip learning using Mach-Zehnder Interferometric (MZI) meshes as synaptic interconnects. A variation of Random Backpropagation (RPB) was experimentally demonstrated on-chip and matched the performance of a standard linear regression on a simple classification task. In addition, we applied the Contrastive Hebbian Learning (CHL) rule to a simulated neural network composed of MZI meshes for a random input-output mapping task. The CHL-trained MZI network performed better than random guessing but did not match the performance of the ideal neural network (without the constraints imposed by the MZI meshes). Through these efforts, we demonstrate that co-integrated CMOS and SiPh technologies are well-suited to the design of scalable SNN computing architectures.

EWB: Event-Based Weight Binarization Algorithm for Spiking Neural Networks

Learning binary weights to minimize the difference between target and actual outputs can be considered as a parameter optimization task within the given constraints, and thus, it belongs to the application domain of the Lagrange multiplier method (LMM). Based on the LMM, we propose a novel event-based weight binarization (eWB) algorithm for spiking neural networks (SNNs) with binary synaptic weights (-1, 1). The algorithm features (i) event-based asymptotic weight binarization using local data only, (ii) full compatibility with event-based end-to-end learning algorithms (e.g., event-driven random backpropagation (eRBP) algorithm), and (iii) the capability to address various constraints (including the binary weight constraint). As a proof of concept, we combine eWB with eRBP (eWB-eRBP) to obtain a single algorithm for learning binary weights to generate correct classifications. Fully connected SNNs were trained using eWB-eRBP and achieved an accuracy of 95.35% on MNIST. To the best of our knowledge, this is the first report on completely binary SNNs trained using an event-based learning algorithm. Given that eRBP with full-precision (32-bit) weights exhibited 97.20% accuracy, the binarization comes at the cost of an accuracy reduction of approximately 1.85%. The python code is available online: https://github.com/galactico7/eWB.

Optimal Distribution of Spiking Neurons Over Multicore Neuromorphic Processors

In a multicore neuromorphic processor embedding a learning algorithm, a presynaptic neuron is occasionally located in a different core from the cores of its postsynaptic neurons, which needs neuron-to-target core communication for inference through a network router. The more neuron-to-target core connections, the more workload is imposed on the network router, which the more likely causes event routing congestion. Another significant challenge arising from a large number of neuron-to-core connections is data duplication in multiple cores for the learning algorithm to access the full data to evaluate weight update. This data duplication consumes a considerable amount of on-chip memory while the memory capacity per core is strictly limited. The optimal distribution of neurons over cores is categorized as an optimization problem with constraints, which may allow the discrete Lagrangian multiplier method (LMM) to optimize the distribution. Proof-of-concept demonstrations were made on the distribution of neurons over cores in a neuromorphic processor embedding a learning algorithm. The choice of the learning algorithm was twofold: a simple spike timing-dependent plasticity learning rule and event-driven random backpropagation algorithm, which are categorized as a two- and three-factor learning rule, respectively. As a result, the discrete LMM significantly reduced the number of neuron-to-core connections for both algorithms by approximately 55% in comparison with the number for random distribution cases, implying a 55% reduction in the workload on the network router and a 52.8% reduction in data duplication. The code is available on-line (https://github.com/guhyunkim/Optimize-neuron-distribution).

Learning in the machine: Recirculation is random backpropagation

Learning in physical neural systems must rely on learning rules that are local in both space and time. Optimal learning in deep neural architectures requires that non-local information be available to the deep synapses. Thus, in general, optimal learning in physical neural systems requires the presence of a deep learning channel to communicate non-local information to deep synapses, in a direction opposite to the forward propagation of the activities. Theoretical arguments suggest that for circular autoencoders, an important class of neural architectures where the output layer is identical to the input layer, alternative algorithms may exist that enable local learning without the need for additional learning channels, by using the forward activation channel as the deep learning channel. Here we systematically identify, classify, and study several such local learning algorithms, based on the general idea of recirculating information from the output layer to the hidden layers. We show through simulations and mathematical derivations that these algorithms are robust and converge to critical points of the global error function. In most cases, we show that these recirculation algorithms are very similar to an adaptive form of random backpropagation, where each hidden layer receives a linearly transformed, slowly-varying, version of the output error.

Neural and Synaptic Array Transceiver: A Brain-Inspired Computing Framework for Embedded Learning.

Embedded, continual learning for autonomous and adaptive behavior is a key application of neuromorphic hardware. However, neuromorphic implementations of embedded learning at large scales that are both flexible and efficient have been hindered by a lack of a suitable algorithmic framework. As a result, most neuromorphic hardware are trained off-line on large clusters of dedicated processors or GPUs and transferred post hoc to the device. We address this by introducing the neural and synaptic array transceiver (NSAT), a neuromorphic computational framework facilitating flexible and efficient embedded learning by matching algorithmic requirements and neural and synaptic dynamics. NSAT supports event-driven supervised, unsupervised and reinforcement learning algorithms including deep learning. We demonstrate the NSAT in a wide range of tasks, including the simulation of Mihalas-Niebur neuron, dynamic neural fields, event-driven random back-propagation for event-based deep learning, event-based contrastive divergence for unsupervised learning, and voltage-based learning rules for sequence learning. We anticipate that this contribution will establish the foundation for a new generation of devices enabling adaptive mobile systems, wearable devices, and robots with data-driven autonomy.

Learning in the machine: Random backpropagation and the deep learning channel

Random backpropagation (RBP) is a variant of the backpropagation algorithm for training neural networks, where the transpose of the forward matrices are replaced by fixed random matrices in the calculation of the weight updates. It is remarkable both because of its effectiveness, in spite of using random matrices to communicate error information, and because it completely removes the taxing requirement of maintaining symmetric weights in a physical neural system. To better understand random backpropagation, we first connect it to the notions of local learning and learning channels. Through this connection, we derive several alternatives to RBP, including skipped RBP (SRBP), adaptive RBP (ARBP), sparse RBP, and their combinations (e.g. ASRBP) and analyze their computational complexity. We then study their behavior through simulations using the MNIST and CIFAR-10 benchmark datasets. These simulations show that most of these variants work robustly, almost as well as backpropagation, and that multiplication by the derivatives of the activation functions is important. As a follow-up, we study also the low-end of the number of bits required to communicate error information over the learning channel. We then provide partial intuitive explanations for some of the remarkable properties of RBP and its variations. Finally, we prove several mathematical results for RBP and its variants including: (1) the convergence to optimal fixed points for linear chains of arbitrary length; (2) convergence to fixed points for linear autoencoders with decorrelated data; (3) long-term existence of solutions for linear systems with a single hidden layer, and their convergence in special cases; and (4) convergence to fixed points of non-linear chains, when the derivative of the activation functions is included.

Learning in the machine: The symmetries of the deep learning channel

In a physical neural system, learning rules must be local both in space and time. In order for learning to occur, non-local information must be communicated to the deep synapses through a communication channel, the deep learning channel. We identify several possible architectures for this learning channel (Bidirectional, Conjoined, Twin, Distinct) and six symmetry challenges: (1) symmetry of architectures; (2) symmetry of weights; (3) symmetry of neurons; (4) symmetry of derivatives; (5) symmetry of processing; and (6) symmetry of learning rules. Random backpropagation (RBP) addresses the second and third symmetry, and some of its variations, such as skipped RBP (SRBP) address the first and the fourth symmetry. Here we address the last two desirable symmetries showing through simulations that they can be achieved and that the learning channel is particularly robust to symmetry variations. Specifically, random backpropagation and its variations can be performed with the same non-linear neurons used in the main input–output forward channel, and the connections in the learning channel can be adapted using the same algorithm used in the forward channel, removing the need for any specialized hardware in the learning channel. Finally, we provide mathematical results in simple cases showing that the learning equations in the forward and backward channels converge to fixed points, for almost any initial conditions. In symmetric architectures, if the weights in both channels are small at initialization, adaptation in both channels leads to weights that are essentially symmetric during and after learning. Biological connections are discussed.