DL4CV at TU München

Arrow

100% for free

Arrow

Efficient learning

Arrow

100% for free

Arrow

Efficient learning

Arrow

Synchronization on all devices

Arrow Arrow

It’s completely free

studysmarter schule studium
d

4.5 /5

studysmarter schule studium
d

4.8 /5

studysmarter schule studium
d

4.5 /5

studysmarter schule studium
d

4.8 /5

Study with flashcards and summaries for the course DL4CV at the TU München

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

What is Self-Supervised Learning?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

How can we restrict degree of freedom/reduced learnable parameters?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

How should be the filter depth dimension?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

How do we get from filters to a ConvNet?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

Why Transfer Learning is good?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

Regularization Techniques?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

Is it ok to treat dimensions separately in Batch Normalilization?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

What is the Depth of Neural Network?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

What if the graph has loop?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

Example of many to one mapping?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

What does KL-Div Loss do in latent space?

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

What is the connection between Autoencoder and PCA?

Your peers in the course DL4CV at the TU München create and share summaries, flashcards, study plans and other learning materials with the intelligent StudySmarter learning app.

Get started now!

Flashcard Flashcard

Exemplary flashcards for DL4CV at the TU München on StudySmarter:

DL4CV

What is Self-Supervised Learning?
Self-supervised learning is a type of supervised learning where the training labels are determined by the input data.

word2vec and similar word embeddings are a good example of self-supervised learning. word2vec models predict a word from its surrounding words (and vice versa). Unlike “traditional” supervised learning, the class labels are not separate from the input data.

Autoencoders are another example of self-supervised learning, as they are trained to shrink and reconstruct their inputs.

DL4CV

How can we restrict degree of freedom/reduced learnable parameters?
1) In conVnets connections are structured (everything is not connected with everything)
2) in convolution wen we apply a filters to different spatial location the weights are shared

DL4CV

How should be the filter depth dimension?
Depth dimension *must* match input depth dimension;i.e., filter extends the full depth of the

DL4CV

How do we get from filters to a ConvNet?
The idea is optimize for filter banks
Filters are spatially-invariant
Extract features at locations
Multiple feature banks per location

DL4CV

Why Transfer Learning is good?
we learning different level of features which we can use for other settings

DL4CV

Regularization Techniques?
Weight Decay
Data Augmentation
Early Stopping
Ensemble
Bagging
Dropout

DL4CV

Is it ok to treat dimensions separately in Batch Normalilization?
Shown empirically that even if features are not decorrelated, convergence is still faster with this method

DL4CV

What is the Depth of Neural Network?
Number of Layers

DL4CV

What if the graph has loop?
we should unroll it and back-propagate it through time

DL4CV

Example of many to one mapping?
Language recognition
Sentimental analysis (grading writings)

DL4CV

What does KL-Div Loss do in latent space?
forcing a unit Gaussian distribution so the latent vector becomes a distribution

DL4CV

What is the connection between Autoencoder and PCA?
PCA is restricted to a linear map, while auto encoders can have nonlinear enoder/decoders.

A single layer auto encoder with linear transfer function is nearly equivalent to PCA, where nearly means that the W
W found by AE and PCA won’t be the same–but the subspace spanned by the respective W
W’s will.

Sign up for free to see all flashcards and summaries for DL4CV at the TU München

Singup Image Singup Image
Wave

Other courses from your degree program

For your degree program 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 page

What is StudySmarter?

What is StudySmarter?

StudySmarter 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 DL4CV 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.

Awards

Best EdTech Startup in Europe

Awards
Awards

EUROPEAN YOUTH AWARD IN SMART LEARNING

Awards
Awards

BEST EDTECH STARTUP IN GERMANY

Awards
Awards

Best EdTech Startup in Europe

Awards
Awards

EUROPEAN YOUTH AWARD IN SMART LEARNING

Awards
Awards

BEST EDTECH STARTUP IN GERMANY

Awards

How it works

Top-Image

Get a learning plan

Prepare for all of your exams in time. StudySmarter creates your individual learning plan, tailored to your study type and preferences.

Top-Image

Create flashcards

Create flashcards within seconds with the help of efficient screenshot and marking features. Maximize your comprehension with our intelligent StudySmarter Trainer.

Top-Image

Create summaries

Highlight the most important passages in your learning materials and StudySmarter will create a summary for you. No additional effort required.

Top-Image

Study alone or in a group

StudySmarter automatically finds you a study group. Share flashcards and summaries with your fellow students and get answers to your questions.

Top-Image

Statistics and feedback

Always keep track of your study progress. StudySmarter shows you exactly what you have achieved and what you need to review to achieve your dream grades.

1

Learning Plan

2

Flashcards

3

Summaries

4

Teamwork

5

Feedback