LearningR | get started with a new RStudio project | Data Visualization library

Your perceptron lacks a bias term, your equation is of form SUM_i w_i x_i, instead of SUM_i w_i x_i + b. With the functional form you have it is impossible to separate points, where the separating hyperplane does not cross the origin (and yours does not). Alternatively you can add a column of "1s" to your data, it will serve the same purpose, as the corresponding w_i will just behave as b (since all x_i will be 1)

Maybe you need to declare optimizer like this: optimizer = itk.QuasiNewtonOptimizerv4Template[itk.D].New()

I do not know very much about stochastic gradient descent but there are two improvements that I spot in your code.

Firstly, the error is caused because you try to multiply a float with a list and add that to a float. This is fixed by using round brackets instead of square:

I believe that saving the optimizer's state is an important aspect of logging and reproducibility. It stores many details about the optimizer's settings; things including the kind of optimizer used, learning rate, weight decay, type of scheduler used (I find this very useful personally), etc. Moreover, it can be used in a similar fashion when loading pre-trained weights into your current model via .load_state_dict() such that you can pass in some stored optimizer setting/configuration into your current optimizer using the same method: optimizer.load_state_dict(some_good_optimizer.state_dict()).

You are very close, but with a couple of problems. First, you need to be doing matrix multiplication. * will do element-wise multiplication (i.e., np.array([1,2,3]) * np.array([2,3,4]) = np.array([2,6,12]). To do matrix multiplication with numpy you can use the @ operator (i.e., matrix1 @ matrix2) or use the np.matmul function.

You other problem is the shape of your inputs. I am not sure why you are adding a 3rd dimension (the 1 at the end of train.reshape(train.shape[0],train.shape[1]*train.shape[2],1). You should be fine keeping it as a matrix (change it to train.reshape(train.shape[0],train.shape[1]*train.shape[2]), change the test.reshape accordingly.

finally, your inference line is a little off: a2=w1*train[i]+w2*trainX[i]+b1

You first must calculate a1 before a2. An important part of matrix multiplication is that inner dimensions must agree (i.e., you cannot multiply matricies of shapes [100,50] and [100, 50] but you can multiply matricies of shapes [100,50] and [50, 60], the resulting shape of the matrix product is the outer indicies of each matrix, in this case [100,60]). As a result of matrix multiplication, you can also get rid of the for loop around training examples. All examples are calculated at the same time. So to calculate a1, we need to transpose our w1 and have it as the right hand variable.

You haven't transferred your test data on the GPU:

CanvasFrame tries to do gamma correction by default because it's typically needed by cameras used for CV, but cheap webcams usually output gamma corrected images, so make sure to let CanvasFrame know about it this way:

I will assume that the chained ifelse is wrong when it assigns the value 2 to two levels of prediction.

The following code works as expected. It removes unnecessary instructions, it uses cut, that returns a factor, and explicitly sets the factor levels.

I don't load nor use package dplyr and use the new (R 4.1.0) operator |> instead of magrittr's %>%.

By default there is no limit. That means it will add all words it finds to the vocabulary.

Also note, the examples you linked to are over 4 years old. I suggest you use the official examples: https://github.com/eclipse/deeplearning4j-examples