convolutional neural networks for sentence classification

The pooled layers (Pooling layer) are also inspired by visual neuroscience. In the primary visual cortex V1 (Primary visual cortex), there are many complex cells (Complex cells) that are invariant to small changes in objects in the image (invariance to small shifts and Distortions). This invariance is also the core of pooling layer, we first see how the pooling layer works, and then specifically analyze this invariance.We illustrate the working process of the pooling layer, in the max pooling op

edge to 256 D to get B, and then in the center of B take 256*256 square picture to get C, and then randomly extract 224*224 on C as a training sample, and then in the combination of image level inverse increase the sample to achieve data gain. This gain method is 2048 times times the sample increase, allowing us to run a larger network.(2) Adjust the RGB valueThe specific idea is: To do PCA analysis of three channel, get the main component, make some jittter in the corresponding dimension, incr

1. Neural networksRoughly speaking, a neural network is a set of connected input/output units. Each connection is associated with a weight. In the learning phase, by adjusting these weights, we can predict the correct class labels of input tuples for learning. Due to the connection between units, neural network learning is also called connectionist learning ).

; -j = j + lambda* (sum(sum(Theta1 (:,2: End). ^2))+sum(sum(Theta2 (:,2: End). ^2)))/2/m; + -%Backward Propagation +Delta1 = zeros (Size (Theta1)); %25x401 ADelta2 = zeros (Size (THETA2)); %0x26 at forI=1: M -DELTA3 = A3 (i,:)'-Y_vect (i,:)'; %0x1 -TEMPTHETA2 = Theta2'* DELTA3;% 26x10x10x1 = 26x1 -Delta2 = TempTheta2 (2: End). * Sigmoidgradient (Z2 (i,:)'); %25x1 -Delta2 = Delta2 + delta3 * A2 (i,:); %10x1x1x26 -Delta1 = Delta1 + delta2 * A1 (I,:); %25x1x1x401 in end; - toTheta2_grad = delt