Your peers in the course Introduction to Deep Learning at the TU München create and share summaries, flashcards, study plans and other learning materials with the intelligent StudySmarter learning app.

Get started now!

Introduction to Deep Learning

When an experienced deep learning engineer works on a new problem, they can usually use insight from previous problems to train a good model on the first try, without needing to iterate multiple times through different models.

False

True

Introduction to Deep Learning

How can we prevent our model from overfitting?

Regularization

Introduction to Deep Learning

Which of the following are true?

X is a matrix in which each column is one training example

a₄[²] is the activation output by the 4th neuron of the 2nd layer

a[²]⁽¹²⁾ denotes activation vector of the 12th layer on the 2nd training example

a[²] denotes the activation vextor of the 2nd layer

a₄[²] is the activation output of the 2nd layer for the 4th training example

a[²]⁽¹²⁾ denotes the activation vector of the 2nd layer for the 12th training example

Introduction to Deep Learning

A demographic dataset with statistics on different cities' population, GPD per capita, economic growth is an example of "unstructured" data because it contains data coming from different sources.

False

True

Introduction to Deep Learning

What does the analogy "AI is the new electricity" refer to?

Similar to electricity starting about 100 years ago, AI is transforming multiple industries

AI is powering personal devices in our homes and offices, similar to elextricity

AI runs on computers and is thus powered by electricity, but it is letting computers do things not possible before

Through the “smart grid”, AI is delivering a new wave of electricity

Introduction to Deep Learning

What is a problem with Gradient Descent?

We can only determine the local minimum and Neural Networks are non-convex -> there are many local minima

But this can be good enough to solve our problem.

Introduction to Deep Learning

List advanced regularization approaches

- Weight Decay
- Early Stopping
- Bagging and Ensemble Methods
- Dropout
- Batch Normalization

Introduction to Deep Learning

What happens if we initialize all weights with small random numbers?

Gradients vanish

Introduction to Deep Learning

What does a neuron compute?

A neuron computes the mean of all features before applying the output to an activation function

A neuron computes an activation function followed by a linear function (z = Wx +b)

A neuron computes a linear function (z = Wx + b) followed by an activation function

A neuron computes a function g that scales the input x linearly (Wx +b)

Introduction to Deep Learning

Why is a Recurrent Neural Network (RNN) used for machine translation?

It can be traiend as a supervised learning problem

It is strictly more powerful than a Convolutional Neural Network (CNN)

It is applicable when the input/output is a sequence (e.g., a sequence of words)

RNNs represent the recurrent process of Idea->Code->Experiment->Idea->…

Introduction to Deep Learning

How does the k-NN Algorithm work?

A classifier that looks at the distance of k neighbors:

1. Load the data

2. Initialise the value of k

3. For gettin the predicted class, iterate from 1 tot toal number of training data points

3.1. Calculate the distance between test data and each row of training data (e.g. Euclidean Distance)

3.2. Add the distance and the index of the example to an ordered collection

4. Sort the calculated distances in ascending order based on distance values

5. Get top k rows from the sorted array

6. Get the most frequent class of theses rows

7. Return the predicted class

8. If regression: return the mean of the K; else: return the mode of the K Labels

Introduction to Deep Learning

What does Cross Validation do?

It tests the effectiveness of a machine learning model: Under-, Over-fitting or Well generalised

For your degree program Computer Science at the TU München there are already many courses on StudySmarter, waiting for you to join them. Get access to flashcards, summaries, and much more.

Back to TU München overview pageStudySmarter is an intelligent learning tool for students. With StudySmarter you can easily and efficiently create flashcards, summaries, mind maps, study plans and more. Create your own flashcards e.g. for Introduction to Deep Learning at the TU München or access thousands of learning materials created by your fellow students. Whether at your own university or at other universities. Hundreds of thousands of students use StudySmarter to efficiently prepare for their exams. Available on the Web, Android & iOS. It’s completely free.

Best EdTech Startup in Europe

1## Learning Plan

2## Flashcards

3## Summaries

4## Teamwork

5## Feedback