Machine Learning Applications in Various Fields
This collection showcases the application of machine learning in different domains such as speech recognition, image recognition, and more. From COVID-19 case prediction to anime face generation, each image represents a specific task that can be accomplished using machine learning models. The course focuses on deep learning and neural networks, covering a range of functions including regression, classification, and sequence analysis. Explore the wide array of HW assignments that delve into practical implementations of machine learning techniques.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Machine Learning Looking for Function Speech Recognition ( )= f How are you Image Recognition ( )= f Cat Playing Go ( )= f 5-5 (next move)
Different types of Functions This course focuses on Deep Learning. f Neural Network
Different types of Functions regression scalar vector classification e.g., image f Matrix Sequence e.g., speech, text text image
HW1: COVID-19 Case Prediction regression scalar vector classification e.g., image f Matrix Sequence e.g., speech, text text image
HW2: Phoneme Classification regression scalar vector classification e.g., image f Matrix Sequence e.g., speech, text text image
HW3: Image Classification regression scalar vector classification e.g., image f Matrix Sequence e.g., speech, text text image
HW4: Speaker Classification regression scalar vector classification e.g., image f Matrix Sequence e.g., speech, text text image
HW5: Machine Translation regression scalar vector classification e.g., image f Matrix Sequence e.g., speech, text text image
HW6: Anime Face Generation regression scalar vector classification e.g., image f Matrix Sequence e.g., speech, text text image
Supervised Learning Lecture 1 - 5 Pok mon or Digimon Training Data Pok mon Pok mon Digimon Digimon labels
Lecture 7: Self-supervised Learning It is not efficient to collect data for each task.
Lecture 7: Self-supervised Learning unlabeled images Are they the same? Develop general purpose knowledge Pre-train Are they the same?
Lecture 7: Self-supervised Learning Fine-tune Pok mon Digimon Develop general purpose knowledge Pre-train Fine-tune orange apple Downstream Tasks
Lecture 7: Self-supervised Learning Pre-trained Model vs. Downstream Tasks (Foundation Model) BERT Operating Systems Applications
BERT 340M parameters Attack on Titan Source of image: https://leemeng.tw/attack_on_bert_transfer_learning_in_nlp.html
BERT Bertolt Hoover 340M parameters Attack on Titan Source of image: https://leemeng.tw/attack_on_bert_transfer_learning_in_nlp.html
GPT-3 Source: https://youtu.be/wJJnjzNlMws T5 GPT-2 BERT ELMo
Lecture 6: Generative Adversarial Network ? ? Function ?? ?? ?? ?? ?? ??? ?? ?? ?? ?? unpaired
Unsupervised Abstractive Summarization https://arxiv.org/abs/1810.02851 summary document Unsupervised Translation https://arxiv.org/abs/1710.04087 https://arxiv.org/abs/1710.11041 Language 1 Language 2 Unsupervised ASR https://arxiv.org/abs/1804.00316 https://arxiv.org/abs/1812.09323 https://arxiv.org/abs/1904.04100 https://arxiv.org/abs/2105.11084 Text Audio
Lecture 12: Reinforcement Learning (RL) Human label Pok mon ? It is challenging to label data in some tasks. Human label ? 3-3 ? We can know the results are good or not. RL
Lecture 8: Anomaly Detection This is a Pok mon . This is a Digimon . I do not know
Lecture 9: Explainable AI This is a Pok mon . Because . Classifier Why do you think this image is a Pok mon?
Lecture 9: Explainable AI Amazing!!!!!! Testing Accuracy: 98.4%
Lecture 9: Explainable AI All the images of Pok mon are PNG, while most images of Digimon are JPEG. loading the files png files have transparent background transparent background becomes black Machine discriminates Pok mon and Digimon based on the background colors.
I will let you know the story after fixing the mistake.
Lecture 10: Model Attack Benign Image Attacked Image Tiger Cat 0.64 Star Fish 1.00
Lecture 10: Model Attack = Benign Image Attacked Image 50x - Tiger Cat 0.64 Star Fish 1.00
Lecture 11: Domain Adaptation Training Data Testing Data 57.5% 99.5% The results are from: http://proceedings.mlr.press/v37/ganin15.pdf
Lecture 13: Network Compression smaller Too Big! Deploying ML models in resource- constrained environments Lower latency, Privacy, etc.
Lecture 14: Life-long Learning I can solve task 1. I can solve tasks 1&2. I can solve tasks 1&2&3. Learning Task 2 Learning Task 1 Learning Task 3 This is the target of life-long learning. What is the challenge?
Lecture 15: Meta learning Few-shot learning is usually achieved by meta-learning. Learn to classify Learning Algorithm
