Selection of Most Appropriate Backpropagation Training Algorithm in Data Pattern Recognition
There are several training algorithms for backpropagation method in neural network. Not all of these algorithms have the same accuracy level demonstrated through the percentage level of suitability in recognizing patterns in the data. In this research tested 12 training algorithms specifically in recognize data patterns of test validity. The basic network parameters used are the maximum allowable epoch = 1000, target error = 10-3, and learning rate = 0.05. Of the twelve training algorithms each performed 20 times looping. The test results obtained that the percentage rate of the great match is trainlm algorithm with alpha 5% have adequate levels of suitability of 87.5% at the level of significance of 0.000. This means the most appropriate training algorithm in recognizing the the data pattern of test validity is the trainlm algorithm.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Accelerated Training through Iterative Gradient Propagation Along the Residual Path
Despite being the cornerstone of deep learning, backpropagation is criticized for its inherent sequentiality, which can limit the scalability of very deep models. Such models faced convergence issues due to vanishing gra…
Pipelined Backpropagation at Scale: Training Large Models without Batches
New hardware can substantially increase the speed and efficiency of deep neural network training. To guide the development of future hardware architectures, it is pertinent to explore the hardware and machine learning pr…
Image ClassificationStochastic OptimizationTowards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
Fine-tuning is the most effective way of adapting pre-trained large language models (LLMs) to downstream applications. With the fast growth of LLM-enabled AI applications and democratization of open-souced LLMs, fine-tun…
Abstractive Text SummarizationBio-Inspired Classification: Combining Information Theory and Spiking Neural Networks -- Influence of the Learning Rules
Training of Spiking Neural Networks (SNN) is challenging due to their unique properties, including temporal dynamics, non-differentiability of spike events, and sparse event-driven activations. In this paper, we widely c…
ClassificationComputational EfficiencyCBP: Backpropagation with constraint on weight precision using a pseudo-Lagrange multiplier method
Backward propagation of errors (backpropagation) is a method to minimize objective functions (e.g., loss functions) of deep neural networks by identifying optimal sets of weights and biases. Imposing constraints on weigh…