I am building a simple multi-layer perceptron that takes an image as an input and gives as an output the classification of the image. My image dataset is composed by grayscale images with size (n x m). I choose as input layer nm input neurons (in reality I am reducing dimensions with PCA, but let's keep it simple). Then I choose intermediate hidden layers. Now what should I choose as my output layer? How many neurons and why? My classification uses, say, L different classes (i.e., L different types of images). Should I use a single output neuron?
Since you have L different classes you should have L output neurons, in keras it would be :
...
previous_layer = tf.keras.layers.Dense(4096)(...)
output = tf.keras.layers.Dense(self.nb_class)(previous_layer)
If you were in a binary classification you would need a sigmoid activation
output = tf.keras.layers.Activation('sigmoid')(output)
If L > 2 then you would go for softmax activation.
output = tf.keras.layers.Activation('softmax')(output)
Last thing, you should try some Convolutions layers before going for Dense layers. Look at VGG16 architecture.
If you want to work with just a single model (ML-NN),
if L = 2,
The number of neurons in the last layer can be just one with sigmoid activation (the most common approach).
You can also avoid sigmoid, and simply use a threshold to do the binary classification.
If L > 2,
The number of neurons should be L with softmax activation.
A special-case is a multi-label classification, in which you want to know if for a sample, there can be multiple classes or not.
Then, use L neurons with sigmoid activation.
Related
Denote a[2, 3] to be a matrix of dimension 2x3. Say there are 10 elements in each input and the network is a two-element classifier (cat or dog, for example). Say there is just one dense layer. For now I am ignoring the bias vector. I know this is an over-simplified neural net, but it is just for this example. Each output in a dense layer of a neural net can be calculated as
output = matmul(input, weights)
Where weights is a weight matrix 10x2, input is an input vector 1x10, and output is an output vector 1x2.
My question is this: Can an entire series of inputs be computed at the same time with a single matrix multiplication? It seems like you could compute
output = matmul(input, weights)
Where there are 100 inputs total, and input is 100x10, weights is 10x2, and output is 100x2.
In back propagation, you could do something similar:
input_err = matmul(output_err, transpose(weights))
weights_err = matmul(transpose(input), output_err)
weights -= learning_rate*weights_err
Where weights is the same, output_err is 100x2, and input is 100x10.
However, I tried to implement a neural network in this way from scratch and I am currently unsuccessful. I am wondering if I have some other error or if my approach is fundamentally wrong.
Thanks!
If anyone else is wondering, I found the answer to my question. This does not in fact work, for a few reasons. Essentially, computing all inputs in this way is like running a network with a batch size equal to the number of inputs. The weights do not get updated between inputs, but rather all at once. And so while it seems that calculating together would be valid, it makes it so that each input does not individually influence the training step by step. However, with a reasonable batch size, you can do 2d matrix multiplications, where the input is batch_size by input_size in order to speed up training.
In addition, if predicting on many inputs (in the test stage, for example), since no weights are updated, an entire matrix multiplication of num_inputs by input_size can be run to compute all inputs in parallel.
I have doubt suppose last layer before softmax layer has 1000 nodes and I have only 10 classes to classify how does softmax layer which should output 1000 probability output only 10 probabilities
The output of the 1000-node layer will be the input to the 10-node layer. Basically,
x_10 = w^T * y_1000
The w has to be of the size 1000 x 10. Now, softmax function will be applied on x_10 to produce the probability output for 10 classes.
You're wrong in your understanding! The 1000 nodes, will output 10 probabilities for EACH example, the softmax is an ACTIVATION function! It will take the linear combination of the previous layer depending on the incoming and outgoing weights, and no matter what, output the number of probabilities equal to the number of class! If you an add more details, like maybe giving an example of what you're neural network looks like, we can help you further and explain in a lot more depth so you understand what's going on!
I've seen that we can use Dense(num_classes, ...) as the output layer, but I've also seen Dense((num_classes-1), ...) especially when talking about binary classification. Which do you use and why?
Here is my 2-cent,
I use Dense(num_classes) because I can compute softmax on the output of this layer.
For a binary classification, we typically use cross-entropy as a loss function. Thus, we only need to compute p(x = 1) and p(x = 0) can be computed as 1 - p(x=1).
For a multiclass classification, the only advantage to reduce the size of output by 1 is to reduce the number parameters because we can compute p(x = k) = 1 - sum_{i=1}^K p(x=i), given that K is the number classes. So if you plan not to use softmax but a different function, maybe you can have the output layer to have (num_classes - 1) units.
I can't understand why dropout works like this in tensorflow. The blog of CS231n says that, "dropout is implemented by only keeping a neuron active with some probability p (a hyperparameter), or setting it to zero otherwise." Also you can see this from picture(Taken from the same site)
From tensorflow site, With probability keep_prob, outputs the input element scaled up by 1 / keep_prob, otherwise outputs 0.
Now, why the input element is scaled up by 1/keep_prob? Why not keep the input element as it is with probability and not scale it with 1/keep_prob?
This scaling enables the same network to be used for training (with keep_prob < 1.0) and evaluation (with keep_prob == 1.0). From the Dropout paper:
The idea is to use a single neural net at test time without dropout. The weights of this network are scaled-down versions of the trained weights. If a unit is retained with probability p during training, the outgoing weights of that unit are multiplied by p at test time as shown in Figure 2.
Rather than adding ops to scale down the weights by keep_prob at test time, the TensorFlow implementation adds an op to scale up the weights by 1. / keep_prob at training time. The effect on performance is negligible, and the code is simpler (because we use the same graph and treat keep_prob as a tf.placeholder() that is fed a different value depending on whether we are training or evaluating the network).
Let's say the network had n neurons and we applied dropout rate 1/2
Training phase, we would be left with n/2 neurons. So if you were expecting output x with all the neurons, now you will get on x/2. So for every batch, the network weights are trained according to this x/2
Testing/Inference/Validation phase, we dont apply any dropout so the output is x. So, in this case, the output would be with x and not x/2, which would give you the incorrect result. So what you can do is scale it to x/2 during testing.
Rather than the above scaling specific to Testing phase. What Tensorflow's dropout layer does is that whether it is with dropout or without (Training or testing), it scales the output so that the sum is constant.
Here is a quick experiment to disperse any remaining confusion.
Statistically the weights of a NN-layer follow a distribution that is usually close to normal (but not necessarily), but even in the case when trying to sample a perfect normal distribution in practice, there are always computational errors.
Then consider the following experiment:
DIM = 1_000_000 # set our dims for weights and input
x = np.ones((DIM,1)) # our input vector
#x = np.random.rand(DIM,1)*2-1.0 # or could also be a more realistic normalized input
probs = [1.0, 0.7, 0.5, 0.3] # define dropout probs
W = np.random.normal(size=(DIM,1)) # sample normally distributed weights
print("W-mean = ", W.mean()) # note the mean is not perfect --> sampling error!
# DO THE DRILL
h = defaultdict(list)
for i in range(1000):
for p in probs:
M = np.random.rand(DIM,1)
M = (M < p).astype(int)
Wp = W * M
a = np.dot(Wp.T, x)
h[str(p)].append(a)
for k,v in h.items():
print("For drop-out prob %r the average linear activation is %r (unscaled) and %r (scaled)" % (k, np.mean(v), np.mean(v)/float(k)))
Sample output:
x-mean = 1.0
W-mean = -0.001003985674840264
For drop-out prob '1.0' the average linear activation is -1003.985674840258 (unscaled) and -1003.985674840258 (scaled)
For drop-out prob '0.7' the average linear activation is -700.6128015029908 (unscaled) and -1000.8754307185584 (scaled)
For drop-out prob '0.5' the average linear activation is -512.1602655283492 (unscaled) and -1024.3205310566984 (scaled)
For drop-out prob '0.3' the average linear activation is -303.21194422742315 (unscaled) and -1010.7064807580772 (scaled)
Notice that the unscaled activations diminish due to the statistically imperfect normal distribution.
Can you spot an obvious correlation between the W-mean and the average linear activation means?
If you keep reading in cs231n, the difference between dropout and inverted dropout is explained.
In a network with no dropout, the activations in layer L will be aL. The weights of next layer (L+1) will be learned in such a manner that it receives aL and produces output accordingly. But with a network containing dropout (with keep_prob = p), the weights of L+1 will be learned in such a manner that it receives p*aL and produces output accordingly. Why p*aL? Because the Expected value, E(aL), will be probability_of_keeping(aL)*aL + probability_of_not_keeping(aL)*0 which will be equal to p*aL + (1-p)*0 = p*aL. In the same network, during testing time there will be no dropout. Hence the layer L+1 will receive aL simply. But its weights were trained to expect p*aL as input. Therefore, during testing time you will have to multiply the activations with p. But instead of doing this, you can multiply the activations with 1/p during training only. This is called inverted dropout.
Since we want to leave the forward pass at test time untouched (and tweak our network just during training), tf.nn.dropout directly implements inverted dropout, scaling the values.
The neural network applications I've seen always learn the weights of their inputs and use fixed "hidden layers".
But I'm wondering about the following techniques:
1) fixed inputs, but the hidden layers are no longer fixed, in the sense that the functions of the input they compute can be tweaked (learned)
2) fixed inputs, but the hidden layers are no longer fixed, in the sense that although they have clusters which compute fixed functions (multiplication, addition, etc... just like ALUs in a CPU or GPU) of their inputs, the weights of the connections between them and between them and the input can be learned (this should in some ways be equivalent to 1) )
These could be used to model systems for which we know the inputs and the output but not how the input is turned into the output (figuring out what is inside a "black box"). Do such techniques exist and if so, what are they called?
For part (1) of your question, there are a couple of relatively recent techniques that come to mind.
The first one is a type of feedforward layer called "maxout" which computes a piecewise linear output function of its inputs.
Consider a traditional neural network unit with d inputs and a linear transfer function. We can describe the output of this unit as a function of its input z (a vector with d elements) as g(z) = w z, where w is a vector with d weight values.
In a maxout unit, the output of the unit is described as
g(z) = max_k w_k z
where w_k is a vector with d weight values, and there are k such weight vectors [w_1 ... w_k] per unit. Each of the weight vectors in the maxout unit computes some linear function of the input, and the max combines all of these linear functions into a single, convex, piecewise linear function. The individual weight vectors can be learned by the network, so that in effect each linear transform learns to model a specific part of the input (z) space.
You can read more about maxout networks at http://arxiv.org/abs/1302.4389.
The second technique that has recently been developed is the "parametric relu" unit. In this type of unit, all neurons in a network layer compute an output g(z) = max(0, w z) + a min(w z, 0), as compared to the more traditional rectified linear unit, which computes g(z) = max(0, w z). The parameter a is shared across all neurons in a layer in the network and is learned along with the weight vector w.
The prelu technique is described by http://arxiv.org/abs/1502.01852.
Maxout units have been shown to work well for a number of image classification tasks, particularly when combined with dropout to prevent overtraining. It's unclear whether the parametric relu units are extremely useful in modeling images, but the prelu paper gets really great results on what has for a while been considered the benchmark task in image classification.