Nearly all state-of-the-art deep learning algorithms rely on error backpropagation, which is generally regarded as biologically implausible. An alternative way of training an artificial neural network is through treating each unit in the network as a reinforcement learning agent, and thus the network is considered as a team of agents. As such, all units can be trained by REINFORCE, a local learning rule modulated by a global signal that is more consistent with biologically observed forms of synaptic plasticity. Although this learning rule follows the gradient of return in expectation, it suffers from high variance and thus the low speed of learning, rendering it impractical to train deep networks. We therefore propose a novel algorithm called MAP propagation to reduce this variance significantly while retaining the local property of the learning rule. Experiments demonstrated that MAP propagation could solve common reinforcement learning tasks at a similar speed to backpropagation when applied to an actor-critic network. Our work thus allows for the broader application of teams of agents in deep reinforcement learning.

Nearly all state-of-the-art deep learning algorithms rely on error backpropagation, which is generally regarded as biologically implausible. An alternative way of training an artificial neural network is through treating each unit in the network as a reinforcement learning agent, and thus the network is considered as a team of agents. As such, all units can be trained by REINFORCE, a local learning rule modulated by a global signal that is more consistent with biologically observed forms of synaptic plasticity. Although this learning rule follows the gradient of return in expectation, it suffers from high variance and thus the low speed of learning, rendering it impractical to train deep networks. We therefore propose a novel algorithm called MAP propagation to reduce this variance significantly while retaining the local property of the learning rule.

A methodology for faster supervised learning in dynamical nonlin(cid:173) ear neural networks is presented. It exploits the concept of adjoint operntors to enable computation of changes in the network's re(cid:173) sponse due to perturbations in all system parameters, using the so(cid:173) lution of a single set of appropriately constructed linear equations. The lower bound on speedup per learning iteration over conven(cid:173) tional methods for calculating the neuromorphic energy gradient is O(N2), where N is the number of neurons in the network.

Temporal action localization in videos presents significant challenges in the field of computer vision. While the boundary-sensitive method has been widely adopted, its limitations include incomplete use of intermediate and global information, as well as an inefficient proposal feature generator. To address these challenges, we propose a novel framework, Sparse Multilevel Boundary Generator (SMBG), which enhances the boundary-sensitive method with boundary classification and action completeness regression. SMBG features a multi-level boundary module that enables faster processing by gathering boundary information at different lengths. Additionally, we introduce a sparse extraction confidence head that distinguishes information inside and outside the action, further optimizing the proposal feature generator. To improve the synergy between multiple branches and balance positive and negative samples, we propose a global guidance loss. Our method is evaluated on two popular benchmarks, ActivityNet-1.3 and THUMOS14, and is shown to achieve state-of-the-art performance, with a better inference speed (2.47xBSN++, 2.12xDBG). These results demonstrate that SMBG provides a more efficient and simple solution for generating temporal action proposals. Our proposed framework has the potential to advance the field of computer vision and enhance the accuracy and speed of temporal action localization in video analysis.The code and models are made available at \url{https://github.com/zhouyang-001/SMBG-for-temporal-action-proposal}.

Real-time search methods, such as LRTA*, have been used to solve awide variety of planning problems because they can make decisions fastand still converge to a minimum-cost plan if they solve the sameplanning task repeatedly. In this paper, we perform an empiricalevaluation of two existing variants of LRTA* that were developed tospeed up its convergence, namely HLRTA* and FALCONS. Our experimentalresults demonstrate that these two real-time search methods havecomplementary strengths and can be combined. We call the new real-timesearch method eFALCONS and show that it converges with fewer actionsto a minimum-cost plan than LRTA*, HLRTA*, and FALCONS.

A methodology for faster supervised learning in dynamical nonlinear neural networks is presented. It exploits the concept of adjoint operntors to enable computation of changes in the network's response due to perturbations in all system parameters, using the solution of a single set of appropriately constructed linear equations. The lower bound on speedup per learning iteration over conventional methods for calculating the neuromorphic energy gradient is O(N2), where N is the number of neurons in the network. 1 INTRODUCTION The biggest promise of artifcial neural networks as computational tools lies in the hope that they will enable fast processing and synthesis of complex information patterns. In particular, considerable efforts have recently been devoted to the formulation of efficent methodologies for learning (e.g., Rumelhart et al., 1986; Pineda, 1988; Pearlmutter, 1989; Williams and Zipser, 1989; Barhen, Gulati and Zak, 1989). The development of learning algorithms is generally based upon the minimization of a neuromorphic energy function. The fundamental requirement of such an approach is the computation of the gradient of this objective function with respect to the various parameters of the neural architecture, e.g., synaptic weights, neural Adjoint Operator Algorithms 499

A methodology for faster supervised learning in dynamical nonlinear neural networks is presented. It exploits the concept of adjoint operntors to enable computation of changes in the network's response due to perturbations in all system parameters, using the solution of a single set of appropriately constructed linear equations. The lower bound on speedup per learning iteration over conventional methods for calculating the neuromorphic energy gradient is O(N2), where N is the number of neurons in the network. 1 INTRODUCTION The biggest promise of artifcial neural networks as computational tools lies in the hope that they will enable fast processing and synthesis of complex information patterns. In particular, considerable efforts have recently been devoted to the formulation of efficent methodologies for learning (e.g., Rumelhart et al., 1986; Pineda, 1988; Pearlmutter, 1989; Williams and Zipser, 1989; Barhen, Gulati and Zak, 1989). The development of learning algorithms is generally based upon the minimization of a neuromorphic energy function. The fundamental requirement of such an approach is the computation of the gradient of this objective function with respect to the various parameters of the neural architecture, e.g., synaptic weights, neural Adjoint Operator Algorithms 499

A methodology for faster supervised learning in dynamical nonlinear neuralnetworks is presented. It exploits the concept of adjoint operntors to enable computation of changes in the network's response dueto perturbations in all system parameters, using the solution of a single set of appropriately constructed linear equations. The lower bound on speedup per learning iteration over conventional methodsfor calculating the neuromorphic energy gradient is O(N2), where N is the number of neurons in the network. 1 INTRODUCTION The biggest promise of artifcial neural networks as computational tools lies in the hope that they will enable fast processing and synthesis of complex information patterns. In particular, considerable efforts have recently been devoted to the formulation ofefficent methodologies for learning (e.g., Rumelhart et al., 1986; Pineda, 1988; Pearlmutter, 1989; Williams and Zipser, 1989; Barhen, Gulati and Zak, 1989). The development of learning algorithms is generally based upon the minimization of a neuromorphic energy function.