### What’s the value of making the RL agent’s output stochastic opposed to deterministic?

I have a question about a reinforcement learning problem. I’m training an agent to add or delete pixels in a [12 x 12] 2D space (going to be 3D in the future). Its action space consists of two discrete outputs: x[0-12] and y[0-12]. What would be the value of instead outputting a (continuous) probabilistic output…

### How can we compute the gradient of max pooling with overlapping regions?

Studying CNN Back-propagation I can’t understand how can we compute the gradient of max pooling with overlapping regions ? That’s also a question from this quiz and can be also found on this book .

### Problem in creating a Numpy Dataset for Classification problem

I am trying to train a classification Model to classify Images, but my images here are Numpy arrays of 1’s and 0’s as shown in the Image, For now, I have tried, x1_data=[] def create_array(columns=5,rows=5,randomness=.3): board = np.zeros([rows,columns],dtype=’int64′) for i in range(rows): for j in range(columns): if np.random.random() <= randomness: board[i,j] = 1 return board…

### Ghost camera or video overlays for example in sports

Secondary camera, ghost overlay, video merge… I do not know if what I mean has a more specific name. I wonder if this is a thing. This could be insightful for example in racing sports where participants race one after another e.g. alpine skiing, downhill mountain bike, showjumping etc. E.g. comparing the current starter to…

### How to draw rectangles for gender classification?

I wonder what is the better way of drawing rectangles on images for gender classification. My task is to create a classifier (CNN based) to detect gender from pictures of entire bodies (not just faces). When I started labeling pictures I noticed that I am not sure whether I should draw it around an entire…

### How to use BERT as a Conversational AI?

I’m looking to make a conversational AI that uses online learning, so it can continue learning after the model has been deployed. At some point in the future, I’d also like to be to use NLP as an interface to direct the AI to accomplish specific tasks. I’m not sure how flexible a conversational AI…

### How to compute number of weights of CNN?

How can we compute number of weights considering a convolutional neural network that is used to classify images into two classes : INPUT: 100×100 gray-scale images. LAYER 1: Convolutional layer with 60 7×7 convolutional filters (stride=1, valid padding). LAYER 2: Convolutional layer with 100 5×5 convolutional filters (stride=1, valid padding). LAYER 3: A max pooling…

### How can we prove that an autoassociator network will continue to perform if we zero the diagonal elements of a weight matrix?

How can I we prove that an autoassociator network will continue to perform if we zero the diagonal elements of a weight matrix that has been determined by the Hebb rule. In other words, suppose that the weight matrix is determined from: \$W = PP^T- QI\$ where \$Q\$ is the number of prototype vectors. Hint…

### Recognition of lines in a chalkboard

I’m trying to develop a real-time application that, from the sequence of chalkboard images captured by a webcam, recognizes the lines being draw on it. It must be able of recognize the lines from the chalkboard background, filter the presence in the image of the teacher, and translate these lines to some representation, something as…

### How to train image segmentation task with only one class?

Is there a neural network that has architecture optimizations for segmenting only one class (object and background)? I have tried U-net but it is not providing good enough results. I am wondering if this can be due to the fact that my dataset has different image resolutions / aspect ratios.