Youtube videos
8 important questions on Youtube videos
How can weights ensure that a unit in a hidden layer becomes sensitive to a specific feature in the picture?
- You want the weights of the connections to that unit to have values so that it becomes active when that specific feature is present in the picture
- that unit must become active when the edge it is sensitive to is present and inactive otherwise.
What does a sigmoid activation do?
- A sigmoid activation ensures that the resulting number is between 0 and 1.
- the value serving as input for the activation can be in any range of numbers, the
sigmoid activation scales this range to be between 0 and 1
How does a bias influence the activation of a unit?
- Without a bias the activation of the unit is fully determined by the weighted input.
- it can be the case however that you only want the unit to become active when it has a weighted input that is higher than some number.
- this number is then the bias which can be included in the weighted inputs to steer it in a favourable direction. The input with added bias is then passed through the activation function.
- Higher grades + faster learning
- Never study anything twice
- 100% sure, 100% understanding
For my 1st exam I got a C. Then, I started looking for ways to learn better and I came across Study Smart. Since then I have scored a A+, A, A- and another A. I highly recommend it to everyone who wants to hear it. I am so happy with it!!
I was struggling to finish all my first-year subjects for 3 years. Then I discovered Study Smart, which helped me to finish all of them within 3 months.
Because of StudySmart, things are going well in many ways. Before, I always had study stress and no time for anything. Now I feel calm and confident (because of the program). I used to score a B, now I usually score an A or A+.
Hey Chris, I really want to thank you very much for developing the platform, I usually got around C for my exams, now I scored an A+, an A and a A- !!
Since using Study Smart, my average has increased significantly. I even completed a statistics course with a A+ while I'm bad at statistics. I took on extra courses this year, because of Study Smart. Thanks so much!
Ever since I started studying with StudySmart I passed all my exams !!! No more re-sits!! At first, I was happy with a pass and now I only get good grades. Many thanks!
I aced all the courses I studied with Study Smart. For law, I first scored a D, and now an A! I’m 100% sure that I’ll pass all the courses I study with Study Smart.
I always thought I studied well. My grades were fine. I could never have imagined that applying these study skills would have such a huge and direct impact on my grades, my speed and the pleasure I have in learning.
For the first time, I finally feel totally confident about the way I learn. I have the perfect overview and make great progress in terms of speed and the grades I get. Thanks, Chris!
I immediately started to enjoy learning again, and my grades soared. All of a sudden, everything went better. I highly recommend Study Smart to all students..
Being able to create my materials online made the process of studying so much smoother and quicker. I no longer have to spend a huge amount of my time on creating my summaries.
At first, my notes were a mess. Now I use Study Smart to take my notes in a perfectly structured way. It helps me to save a lot of time and do other things I enjoy.
Students that study with Study Smart get better grades. The system applies all the learning methods in such a way that both well-performing students and students who struggle perform much better.
Hi Chris, I would like to thank you very much. Last year I scored C on a course, and this year I got an A+ thanks to your method! Thank you very much!
The largest effect is that my child is more enthusiastic about school! Every parent wants their children to be happy at school, Study Smart made it happen.
In high school, I failed several exams, and that has really changed now. I actually needed this tool very much back then. Since I started studying with StudySmart, I haven't had any D's. My average score is now an A and those are results I would have never had in the past
With my old method, I passed only 3 out of 8 courses. Since I started taking my notes digitally in Study Smart, I have passed all my courses on the first try. For me, StudySmart takes away the stress of wondering if I will pass or not.
Thanks to StudySmart, I passed all my exams, and with better grades than before! On top of that, I have mastered a very good study method now, which I am confident will help me earn my degree.
How many weights and biases are there between one input layer of 784 units and a hidden layer of 16 units, assuming these are dense layers?
- Each unit of the input layer is connected to each unit in the hidden layer. One unit in the hidden layer has 784 connections and thus 784 weights. Counting all 16 hidden units that is 784 * 16 weights.
- each unit in the hidden layer has a bias, thus additionally to the weights there are 16 biases.
How can the cost/ loss function be thought of?
- The cost function can be though of as a function itself similarly to how the neural network is a big function as well.
- it takes the weights and biases of the neural networks as input and the output is the loss
Considering a single weight, how would you know how to update it?
- The value of the weight can be plotted against the loss values corresponding to each weight value
- weight on x, loss on y.
- at any given point, the derivative of the function can be calculated.
- if the derivative is negative, the weight needs to be increased to move closer to the minimum
- if the derivative is positive, the weight needs to be decreased to move closer to the minimum.
A usefull trick is to decrease weight adjustment sizes to prevent overshooting as you approach the local minimum.
What information does the gradient vector of gradient descent tell you?
- The (negative) gradient vector holds all changes made to all weights. It tells you in which way to change which weights in order to decrease the loss function the quickest.
- the sign of the change tells you whether the weight should increase or decrease
- the size of the change tells you how large the adjustment should be
- the adjustment size also tells you how influential that weight is for the loss function, a big change in a weight indicates that that weight is an important pawn in finding the local minimum.
How can you, for the mnist data, identify what the first hidden layer is sensitive to?
- For each neuron you can make a grid of 28 by 28 with the weights of each input.
- these weight grid's tell you which input is most important to each neuron.
- apparently the units do not really look for specific things, it looks fairly random.
The question on the page originate from the summary of the following study material:
- A unique study and practice tool
- Never study anything twice again
- Get the grades you hope for
- 100% sure, 100% understanding
