Few Shot Learning - EXPLAINED!

preview_player
Показать описание

TIMESTAMPS
0:00 Case Study
1:37 Prior Knowledge
3:07 Disadvantage of Traditional Models
4:57 The new Model – explained
6:40 Math
9:04 Code

REFERENCES
  1. CodeEmporium
  2. Machine Learning
  3. Deep Learning
  4. Data Science
  5. Artificial Intelligence
  6. Neural Network
Рекомендации по теме
Few Shot Learning 0:10:01

Few Shot Learning - EXPLAINED!

Few-Shot Learning (1/3): 0:18:39

Few-Shot Learning (1/3): Basic Concepts

What is Zero-Shot 0:08:55

What is Zero-Shot Learning?

Zero-shot, One-shot and 0:03:46

Zero-shot, One-shot and Few-shot Prompting Explained | Prompt Engineering 101

Episode 57: Few-Shot 0:01:36

Episode 57: Few-Shot Learning Explained

Few Shot Learning 0:13:50

Few Shot Learning with Code - Meta Learning - Prototypical Networks

[Few-shot learning][2.2] Prototypical 0:22:18

[Few-shot learning][2.2] Prototypical Networks: intuition, algorithm, pytorch code

C4W4L02 One Shot 0:04:45

C4W4L02 One Shot Learning

AI First Principles: 0:47:15

AI First Principles: Effective Communication & Collaboration with AI tools

Multimodal Few-Shot Learning 0:21:01

Multimodal Few-Shot Learning with Frozen Language Models | Paper Explained

Few-shot and Zero-shot 0:21:31

Few-shot and Zero-shot Learning - Part 01

All Machine Learning 0:16:30

All Machine Learning algorithms explained in 17 min

Few-Shot Prompting Explained 0:10:44

Few-Shot Prompting Explained

Few-shot Learning Explained 0:01:39

Few-shot Learning Explained (FSL): AI with Minimal Data

few shot, zero 0:00:52

few shot, zero shot learning explained #deeplearning #artificialintelligence #shorts

Few-Shot Learning Through 0:34:38

Few-Shot Learning Through an Information Retrieval Lens | TDLS

Few-shot Learning | 0:11:09

Few-shot Learning | Lecture 72 (Part 2) | Applied Deep Learning (Supplementary)

Corporate-Talk Chatbot: Few-Shot 0:01:00

Corporate-Talk Chatbot: Few-Shot Learning, Large Language Models Explained Prompt Engineering Course

Mengye Ren - 0:54:33

Mengye Ren - Towards Continual and Compositional Few-shot Learning

Zero-Shot Learning - 0:29:08

Zero-Shot Learning - Dr. Timothy Hospedales

FEW-SHOT LEARNING | 0:08:54

FEW-SHOT LEARNING | Basic concepts | Introduction to Natural Language Processing (NLP) | 02

Master the Perfect 0:08:30

Master the Perfect ChatGPT Prompt Formula (in just 8 minutes)!

Learning What Not 0:04:40

Learning What Not To Segment: A New Perspective on Few Shot Segmentation | CVPR 2022

Meta-Learning of Neural 0:05:01

Meta-Learning of Neural Architectures for Few-Shot Learning

Комментарии
Автор

Hey this channel is my fav, glad you're back

atifadib
Автор

Glad to see you're back. This channel deserved more than 41k Subs! Keep it up!

PD-vtfe
Автор

8:55 - but if it’s the same network used to process image i and j, how exactly do you tune its parameters? Tuning it to make A embedding look closer to B embedding will also change the B embedding values in the same time.

KlimovArtem
Автор

So can someone help me, if the network can only tell if two images are the same or not, what is the actual learning done here? Isn't it just a image to vec compare? Also how does this help with the original problem is it sam or not? Thanks in advance!

McMurchie
Автор

How does zero shot learning fits into this example?

rochaksaini
Автор

Your videos are really informative and entertaining.

IdiotDeveloper
Автор

Thank you very much for the explanation. But I still don't understand how I can pretrain the similarity function, how should I organize its inputs, etc. Can you explain a little bit more about it?

luansouzasilva
Автор

so during training we still have plenty of data to train the model, including data from same category right?

I am first time learner, the name sounds to me even during training we only have very few data, or one example per category.

Thanks for the video!

linzhu
Автор

can you provide a cosine similarity code using TensorFlow ; pls?

aliboudjema
Автор

Hey can u please send link me to the original GAN video

quadhd
Автор

Thank you very much for the explanation.

TUNBOSUNADEREMI
Автор

Do the final embeddings of the trained network make any human readable sense? Like, hair color, face roundness, etc.

KlimovArtem
Автор

Amazing. If possible cover the coding part as well. Good luck.

helloansuman
Автор

Wow nice video
I learned new things
And your's secondary voice is makes me fun😅😂🤣 bye bye

o__bean__o
Автор

Hey, I've really enjoyed all your videos! Very nicely done at an appropriate technical level. I'd say the name of your channel is a bit misleading. It could also be affecting the number of your subscribers... Keep up the good work. Much appreciated!

somerset
Автор

What about prior knowledge you did not go into it.

kryogenica
Автор

I learned i either have half a brain or just face blindness

kenonerboy
Автор

Several amateur problems here: 1. All, so called "prior" knowledge must be handled on preprocessing stage. Like Face detection, for example. First "cook" the data, then "eat". 2 Huge misunderstanding across entire AI/ML community. You professors didn't teach you that there is a huge difference between an array and a vector. Not every array is a vector! Performing "similarity" functions, or any vector function, on an array is useless and you will always get an illusion of recognition. There will always be "weird" cases where you will not be able to explain the decision made by your model.

Estereos
Автор

Dude, this loss function wouldn't work at all in practice. Think about it first before posting video....

Let's discuss positive case only for actual similar pair,
Let's say distance = 0, so sigmoid(0)=0.5 and loss=-log(0.5) = 0.69

And similarity = inverse(distance) = 1/(1+distance)

That's why folks use contrastive loss.

Sn-nwzb