Sentence examples for using a learning rule from inspiring English sources
Training a network by storing memories at different intensities is equivalent to using a learning rule incorporating weight decay.
This model demonstrates the use of GPU programming (with CUDA) to simulate a two-layer network of Integrate-and-Fire neurons with varying degrees of recurrent connectivity and to investigate its ability to learn a simplified navigation task using a learning rule stemming from Reinforcement Learning, a policy-gradient rule.
The generated membership function parameters are then tuned (parameter identification) using a learning rule such as the BP algorithm.
The update is conducted using a learning rule to train neurons, e.g. n i (t + 1) = n i (t) + α (t) f i (t) [ x t) - n i (t)], where i is the i th neuron; x t) is an input vector from the input data set at time t; and α(t) is the learning rate at time t.
Additionally, the adaptation step uses a learning rule to modify and update the weights.
First, our cerebellar model used a learning rule that simulated supervised learning that takes place in the cerebellum and driven by the climbing fibers messages issued from the inferior olive.
In this paper, a new approach, referred to as EX-SJFEsTLA, is proposed to improve the rule scheduling process, using a learning automaton.
To achieve this phase of ANFIS system learning, a gradient descent algorithm with a least squares estimation using a hybrid learning rule is proposed as shown in Table 3.
In traditional behind the ear digital hearing aids, feedback cancellation is usually achieved using an adaptive finite impulse response filter, the weights of which are updated using a suitable learning rule.
For example, a recent neocognitron uses a new learning rule, named add-if-silent, which makes the learning process much simpler and more stable.
Biologically plausible systems for object recognition need to have not only the properties described here, but also mechanisms that use a local learning rule, no separate teacher for each output neuron in a supervised learning scheme, and no lateral copying of weights (Rolls 2016).
