A Framework for the Development of Globally Convergent Adaptive Learning Rate Algorithms
نویسندگان
چکیده
In this paper we propose a framework for developing globally convergent batch training algorithms with adaptive learning rate. The proposed framework provides conditions under which global convergence is guaranteed for adaptive learning rate training algorithms. To this end, the learning rate is appropriately tuned along the given descent direction. Providing conditions regarding the search direction and the corresponding stepsize length this framework can also guarantee global convergence for training algorithms that use a different learning rate for each weight. To illustrate the effectiveness of the proposed approach on various training algorithms simulation results are provided. Key-Words: Global convergence, learning rate adaptation, batch training algorithms, steepest descent, feedforward neural networks.
منابع مشابه
Reinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملReinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملGlobally Convergent Newton Algorithms for Blind Decorrelation
This paper presents novel Newton algorithms for the blind adaptive decorrelation of real and complex processes. They are globally convergent and exhibit an interesting relationship with the natural gradient algorithm for blind decorrelation and the Goodall learning rule. Indeed, we show that these two later algorithms can be obtained from their Newton decorrelation versions when an exact matrix...
متن کاملGlobally convergent algorithms with local learning rates
A novel generalized theoretical result is presented that underpins the development of globally convergent first-order batch training algorithms which employ local learning rates. This result allows us to equip algorithms of this class with a strategy for adapting the overall direction of search to a descent one. In this way, a decrease of the batch-error measure at each training iteration is en...
متن کاملThe Time Adaptive Self Organizing Map for Distribution Estimation
The feature map represented by the set of weight vectors of the basic SOM (Self-Organizing Map) provides a good approximation to the input space from which the sample vectors come. But the timedecreasing learning rate and neighborhood function of the basic SOM algorithm reduce its capability to adapt weights for a varied environment. In dealing with non-stationary input distributions and changi...
متن کامل