Bayes classifier results on a sliding scale - machine-learning

So, I have a Naive Bayes classifier that predicts the mood of a given phrase or sentence. The actual classification works great but I'm having trouble coming up with a visualization for it.
Simple example of classification:
"Yellow flowers are fantastic"
Mood probabilities:
55% Excited
5% Happy
5% Neutral
5% Sad
30% Angry
Here, the singular predicted mood is Excited, with a probability of 55%.
My idea for a visualization was to show only the two extremes: Excited and Angry. In this first example, the scale might look something like this: Figure 1
However, let's say the prediction was something like this:
1% Excited
1% Happy
1% Neutral
96% Sad
1% Angry
I would expect the scale to look like so: Figure 2:
How could i get the indicator to essentially the 66% point from this data that I have?

Related

Accuracy below 50% for binary classification

I am training a Naive Bayes classifier on a balanced dataset with equal number of positive and negative examples. At test time I am computing the accuracy in turn for the examples in the positive class, negative class, and the subsets which make up the negative class. However, for some subsets of the negative class I get accuracy values lower than 50%, i.e. random guessing. I am wondering, should I worry about these results being much lower than 50%? Thank you!
It's impossible to fully answer this question without specific details, so here instead are guidelines:
If you have a dataset with equal amounts of classes, then random guessing would give you 50% accuracy on average.
To be clear, are you certain your model has learned something on your training dataset? Is the training dataset accuracy higher than 50%? If yes, continue reading.
Assuming that your validation set is large enough to rule out statistical fluctuations, then lower than 50% accuracy suggests that something is indeed wrong with your model.
For example, are your classes accidentally switched somehow in the validation dataset? Because notice that if you instead use 1 - model.predict(x), your accuracy would be above 50%.

FaceNet for dummies

The FaceNet algorithm (described in this article) uses a convolutional neural network to represent an image in an 128 dimensional Euclidean space.
While reading the article I didn't understand:
How does the loss function impact on the convolutional network (in normal networks, in order to minimize the loss the weights are slightly changed -
backpropagation - so, what happens in this case?)
how are the triplets chosen?
2.1 . how do I know a negative image is hard
2.2 . why am I using the loss function to determine the negative image
2.3 . when do I check my images for hardness with respect to the anchor - I believe that is before I send a triplet to be processed by the network, right.
Here are some of the answer that may clarify your doubts:
Even here the weights are adjusted to minimise the Loss, its just the loss term is little complicated. The loss has two parts(separated by + in the equation), first part is the image of a person compared to a different image of the same person. The second part is the image of the person compared to a image of a different person. We want the first part loss to be less than the second part loss and the loss equation in essence captures that. So here you basically want to adjust the weights such that same person error is less and different person error is more.
The Loss term involves three images: The image in question(anchor): x_a, its positive pair: x_p and its negative pair: x_n. An hardest positive of x_a is the positive image that has the biggest error compared to the rest of the positive images. The hardest negative of x_a is the closest image of a different person. So you want to bring the furthest positives to be close to each other and push the closest negatives further away. This is captured in the loss equation.
Facenet calculates its anchor during training (online). In each minibatch(which is a set of 40 images) they select the hardest negative to the anchor and instead of choosing the hardest positive image, they choose all anchor-positive pairs within the batch.
If you are looking to implement face recognition, you should better consider this paper, that implements centre loss, which is much easier to train and shown to perform better.

Will larger batch size make computation time less in machine learning?

I am trying to tune the hyper parameter i.e batch size in CNN.I have a computer of corei7,RAM 12GB and i am training a CNN network with CIFAR-10 dataset which can be found in this blog.Now At first what i have read and learnt about batch size in machine learning:
let's first suppose that we're doing online learning, i.e. that we're
using a mini­batch size of 1. The obvious worry about online learning
is that using mini­batches which contain just a single training
example will cause significant errors in our estimate of the gradient.
In fact, though, the errors turn out to not be such a problem. The
reason is that the individual gradient estimates don't need to be
super­accurate. All we need is an estimate accurate enough that our
cost function tends to keep decreasing. It's as though you are trying
to get to the North Magnetic Pole, but have a wonky compass that's
10­-20 degrees off each time you look at it. Provided you stop to
check the compass frequently, and the compass gets the direction right
on average, you'll end up at the North Magnetic Pole just
fine.
Based on this argument, it sounds as though we should use online
learning. In fact, the situation turns out to be more complicated than
that.As we know we can use matrix techniques to compute the gradient
update for all examples in a mini­batch simultaneously, rather than
looping over them. Depending on the details of our hardware and linear
algebra library this can make it quite a bit faster to compute the
gradient estimate for a mini­batch of (for example) size 100 , rather
than computing the mini­batch gradient estimate by looping over the
100 training examples separately. It might take (say) only 50 times as
long, rather than 100 times as long.Now, at first it seems as though
this doesn't help us that much.
With our mini­batch of size 100 the learning rule for the weights
looks like:
where the sum is over training examples in the mini­batch. This is
versus for online learning.
Even if it only takes 50 times as long to do the mini­batch update, it
still seems likely to be better to do online learning, because we'd be
updating so much more frequently. Suppose, however, that in the
mini­batch case we increase the learning rate by a factor 100, so the
update rule becomes
That's a lot like doing separate instances of online learning with a
learning rate of η. But it only takes 50 times as long as doing a
single instance of online learning. Still, it seems distinctly
possible that using the larger mini­batch would speed things up.
Now i tried with MNIST digit dataset and ran a sample program and set the batch size 1 at first.I noted down the training time needed for the full dataset.Then i increased the batch size and i noticed that it became faster.
But in case of training with this code and github link changing the batch size doesn't decrease the training time.It remained same if i use 30 or 128 or 64.They are saying that they got 92% accuracy.After two or three epoch they have got above 40% accuracy.But when i ran the code in my computer without changing anything other than the batch size i got worse result after 10 epoch like only 28% and test accuracy stuck there in the next epochs.Then i thought since they have used batch size of 128 i need to use that.Then i used the same but it became more worse only give 11% after 10 epoch and stuck in there.Why is that??
Neural networks learn by gradient descent an error function in the weight space which is parametrized by the training examples. This means the variables are the weights of the neural network. The function is "generic" and becomes specific when you use training examples. The "correct" way would be to use all training examples to make the specific function. This is called "batch gradient descent" and is usually not done for two reasons:
It might not fit in your RAM (usually GPU, as for neural networks you get a huge boost when you use the GPU).
It is actually not necessary to use all examples.
In machine learning problems, you usually have several thousands of training examples. But the error surface might look similar when you only look at a few (e.g. 64, 128 or 256) examples.
Think of it as a photo: To get an idea of what the photo is about, you usually don't need a 2500x1800px resolution. A 256x256px image will give you a good idea what the photo is about. However, you miss details.
So imagine gradient descent to be a walk on the error surface: You start on one point and you want to find the lowest point. To do so, you walk down. Then you check your height again, check in which direction it goes down and make a "step" (of which the size is determined by the learning rate and a couple of other factors) in that direction. When you have mini-batch training instead of batch-training, you walk down on a different error surface. In the low-resolution error surface. It might actually go up in the "real" error surface. But overall, you will go in the right direction. And you can make single steps much faster!
Now, what happens when you make the resolution lower (the batch size smaller)?
Right, your image of what the error surface looks like gets less accurate. How much this affects you depends on factors like:
Your hardware/implementation
Dataset: How complex is the error surface and how good it is approximated by only a small portion?
Learning: How exactly are you learning (momentum? newbob? rprop?)
I'd like to add to what's been already said here that larger batch size is not always good for generalization. I've seen these cases myself, when an increase in batch size hurt validation accuracy, particularly for CNN working with CIFAR-10 dataset.
From "On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima":
The stochastic gradient descent (SGD) method and its variants are
algorithms of choice for many Deep Learning tasks. These methods
operate in a small-batch regime wherein a fraction of the training
data, say 32–512 data points, is sampled to compute an approximation
to the gradient. It has been observed in practice that when using a
larger batch there is a degradation in the quality of the model, as
measured by its ability to generalize. We investigate the cause for
this generalization drop in the large-batch regime and present
numerical evidence that supports the view that large-batch methods
tend to converge to sharp minimizers of the training and testing
functions—and as is well known, sharp minima lead to poorer
generalization. In contrast, small-batch methods consistently converge
to flat minimizers, and our experiments support a commonly held view
that this is due to the inherent noise in the gradient estimation. We
discuss several strategies to attempt to help large-batch methods
eliminate this generalization gap.
Bottom-line: you should tune the batch size, just like any other hyperparameter, to find an optimal value.
The 2018 opinion retweeted by Yann LeCun is the paper Revisiting Small Batch Training For Deep Neural Networks, Dominic Masters and Carlo Luschi suggesting a good generic maximum batch size is:
32
With some interplay with choice of learning rate.
The earlier 2016 paper On Large-batch Training For Deep Learning: Generalization Gap And Sharp Minima gives some reason for not using big batches, which I paraphrase badly, as big batches are likely to get stuck in local (“sharp”) minima, small batches not.

OpenCV HaarCascade Training for Flowers

I have decided to train Haar classifier for 102 flower categories given here:(The dataset)
http://www.robots.ox.ac.uk/~vgg/data/flowers/102/categories.html
In the link you can see several categories. I am posting a few images of an individual flower to explain the question.
This flower belongs to a single class. I have 250 images as positives. There is a considerable variation in this flower's others images(of color, brightness, orientation, etc.). I am hunting for negative images right now. As you might have guessed, I didn't click these pictures so I can't go to the places where these were clicked to collect negative dataset. Instead, I have decided to extract frames from a video. Here is the link:
https://www.youtube.com/watch?v=x3zT1mJE0W0
Here are the images from the video:
It is a video of general garden with bushes and plants background.
My question is: Will this video(and other similar videos) suffice for being negative samples for successful detection? Is it safe to train the classifier for these flowers at all?(I mean with lot of variation in the background. I also plan to use the rest flowers category images as negatives that I am not detecting except the flower that I am trying to detect which in the case here is the Passion Flower).
This is my first training and I am asking this because the training is gonna eat my whole day and night. I am skeptical about it beforehand.
The trick with negative images is to use whatever you have, and as many as possible. The more difference, and quantity, of your negative images means that you will end up with a more robust classifier.
As for your specific question about whether the bushes are a good negative data set compared to the flowers I would say they will be ok. The background behind the bushes is relatively similar and you have quite a distinct flower pattern for your positive samples.

Multilayer perceptron for ocr works with only some data sets

NEW DEVELOPMENT
I recently used OpenCV's MLP implementation to test whether it could solve the same tasks. OpenCV was able to classify the same data sets that my implementation was able to, but unable to solve the one's that mine could not. Maybe this is due to termination parameters (determining when to end training). I stopped before 100,000 iterations, and the MLP did not generalize. This time the network architecture was 400 input neurons, 10 hidden neurons, and 2 output neurons.
I have implemented the multilayer perceptron algorithm, and verified that it works with the XOR logic gate. For OCR I taught the network to correctly classify letters of "A"s and "B"s that have been drawn with a thick drawing untensil (a marker). However when I try to teach the network to classify a thin drawing untensil (a pencil) the network seems to become stuck in a valley and unable to classify the letters in a reasonable amount of time. The same goes for letters I drew with GIMP.
I know people say we have to use momentum to get out of the valley, but the sources I read were vague. I tried increasing a momentum value when the change in error was insignificant and decreasing when above, but it did not seem to help.
My network architecture is 400 input neurons (one for each pixel), 2 hidden layers with 25 neurons each, and 2 neurons in the output layer. The images are gray scale images and the inputs are -0.5 for a black pixel and 0.5 for a white pixel.
EDIT:
Currently the network is trainning until the calculated error for each trainning example falls below an accepted error constant. I have also tried stopping trainning at 10,000 epochs, but this yields bad predictions. The activation function used is the sigmoid logistic function. The error function I am using is the sum of the squared error.
I suppose I may have reached a local minimum rather than a valley, but this should not happen repeatedly.
Momentum is not always good, it can help the model to jump out of the a bad valley but may also make the model to jump out of a good valley. Especially when the previous weights update directions is not good.
There are several reasons that make your model not work well.
The parameter are not well set, it is always a non-trivial task to set the parameters of the MLP.
An easy way is to first set the learning rate, momentum weight and regularization weight to a big number, but to set the iteration (or epoch) to a very large weight. Once the model diverge, half the learning rate, momentum weight and regularization weight.
This approach can make the model to slowly converge to a local optimal, and also give the chance for it to jump out a bad valley.
Moreover, in my opinion, one output neuron is enough for two class problem. There is no need to increase the complexity of the model if it is not necessary. Similarly, if possible, use a three-layer MLP instead of a four-layer MLP.

Resources