lectures | University courses and other presentations

Suppose you have a neural network with 2 layers A and B. A gets the network input. A and B are consecutive (A's output is fed into B as input). Both A and B output predictions (prediction1 and prediction2) Picture of the described architecture You calculate a loss (loss1) directly after the first layer (A) with a target (target1). You also calculate a loss after the second layer (loss2) with its own target (target2).

Does it make sense to use the sum of loss1 and loss2 as the error function and back propagate this loss through the entire network? If so, why is it "allowed" to back propagate loss1 through B even though it has nothing to do with it?

This question is related to this question https://datascience.stackexchange.com/questions/37022/intuition-importance-of-intermediate-supervision-in-deep-learning but it does not answer my question sufficiently. In my case, A and B are unrelated modules. In the aforementioned question, A and B would be identical. The targets would be the same, too.

(Additional information) The reason why I'm asking is that I'm trying to understand LCNN (https://github.com/zhou13/lcnn) from this paper. LCNN is made up of an Hourglass backbone, which then gets fed into MultiTask Learner (creates loss1), which in turn gets fed into a LineVectorizer Module (loss2). Both loss1 and loss2 are then summed up here and then back propagated through the entire network here.

Even though I've visited several deep learning lectures, I didn't know this was "allowed" or makes sense to do. I would have expected to use two loss.backward(), one for each loss. Or is the pytorch computational graph doing something magical here? LCNN converges and outperforms other neural networks which try to solve the same task.

I am implementing a seminar application with twilio programmable video. The scenario can be described as following:

1 host lectures n participants. The participants can participate only via audio but can see the hosts video. I accomplished that by simply unpublishing and disabling the videostreams of the participants:

Much like the title says. I have followed my class tutorials but chunks seem to be missing and it gets a bit confusing flicking between video lectures and pdf's when you're not too well versed in such.

When the app is executed the user can search for a song by year, or display all records within the database. However, originally all records would display from clicking the search by year button instead of the display all button. The search function works as intended but the display all button I cannot seem to figure out, despite following my lecturer's tutorials.

The first section of code is "MainActivity.java" and the second is "OpenDatabse.java"

I am trying to make source and run r script in another r script at the same time

After going through some lectures on class and objects, what I have understood is that if a function is a part of a class then it can be accessed by object which is known as method and if a function is outside a class, then it can be accessed directly.

So for example -

1)

I am struggling with understanding why this while loop (below in the code) terminates after 2 iterations only.

It is from an adative-step size RungeKutta45 Fehlberg Method (https://www.uni-muenster.de/imperia/md/content/physik_tp/lectures/ss2017/numerische_Methoden_fuer_komplexe_Systeme_II/rkm-1.pdf) page 10/11.

The below results in this output:

I am new to the world of the cloud and trying to get my head around some confusion I have while watching foundational lectures on A cloud guru.

I am going through Azure lectures where they explain the basic difference between regions and availability zones.

Now according to MSDN documentation,

Availability Zones is a high-availability offering that protects your applications and data from datacenter failures. Availability Zones are unique physical locations within an Azure region. Each zone is made up of one or more datacenters equipped with independent power, cooling, and networking.

Also, given that each availability zones have multiple data centers it should be all the more reason and intuitive to think that in contrast to regions, availability zones provide both Fault Tolerance and High Availability, but the lecture on Acloud Guru states otherwise,

Also, if availability zones have multiple datacenters, does that imply that regions have 1 datacenter?

I am trying to get a search request from Google by Custom Search API, this product few types of API, some of them are free, more detail here. I know how to create a URL for Custom Search JSON API which has a limit of 100 queries. Custom Search JSON API URL:

I am trying to design an infinite (or a user-defined length) loop that would be independent of my GUI process. I know how to start that loop in a separate thread, so the GUI process is not blocked. However, I would like to have a possibility to interrupt the loop at a press of a button. The complete scenario may look like this:

GUI::startButton->myClass::runLoop... ---> starts a loop in a new thread

GUI::stopButton->myClass::terminateLoop ---> should be able to interrupt the started loop

The problem I have is figuring out how to provide the stop functionality. I am sure there is a way to achieve this in C++. I was looking at a number of multithreading related posts and articles, as well as some lectures on how to use async and futures. Most of the examples did not fit my intended use and/or were too complex for my current state of skills.

Example:

GUIClass.cpp