動画検索
関連広告
検索結果
Introduction
What you don’t need to do deep learning
What is the point of learning deep learning
Neural Nets: a brief history
Top to bottom learning approach
The software stack
Git Repositories
First practical exercise in Jupyter Notebook
Interpretation and explanation of the exercise
Stochastic Gradient Descent (SGD)
Consider how a model interacts with its environment
"doc" function and fastai framework documentation
Image Segmentation
Classifying a review's sentiment based on IMDB text reviews
Predicting salary based on tabular data from CSV
Lesson Summary
Introduction
What has changed since 2015
Images are made of numbers
Downloading images
Training the model and making a prediction
What can deep learning do now
How the course will be taught. Top down learning
Jeremy Howard’s qualifications
Visualizing layers of a trained neural network
Image classification applied to audio
Pytorch vs Tensorflow
Example of how Fastai builds off Pytorch (AdamW optimizer)
Bird or not bird? & explaining some Kaggle features
Best practice - viewing your data between steps
Datablocks API overarching explanation
Where to find fastai documentation
Fastai’s learner (combines model & data)
What’s a pretrained model?
Testing your model with predict method
Segmentation code explanation
Tabular analysis with fastai
Collaborative filtering (recommendation system) example
How to turn your notebooks into a presentation tool (RISE)
What can deep learning do presently?
Homework
Introduction
Linear model and neural net from scratch
Cleaning the data
Setting up a linear model
Creating functions
Doing a gradient descent step
Training the linear model
Measuring accuracy
Using sigmoid
Submitting to Kaggle
Using matrix product
A neural network
Deep learning
Linear model final thoughts
Why you should use a framework
Prep the data
Train the model
Submit to Kaggle
Ensembling
Framework final thoughts
How random forests really work
Data preprocessing
Binary splits
Final Roundup
Practical Deep Learning for Coders ... This free course is designed for people with some coding experience who want to learn how to apply deep ...
YouTube-Jeremy Howard
2024/02/17Introduction
Deep learning in one slide
History of ideas and tools
Simple example in TensorFlow
TensorFlow in one slide
Deep learning is representation learning
Why deep learning (and why not)
Challenges for supervised learning
Key low-level concepts
Higher-level methods
Toward artificial general intelligence
Introduction
2. The number one rule of ML
6. What can deep learning be used for?
10. How to (and how not to) approach this course
14. Creating tensors
20. Matrix multiplication
27. Selecting data (indexing)
30. Accessing a GPU
35. Creating a dataset with linear regression
41. Checking out the internals of our model
45. PyTorch training loop intuition
54. Putting everything together
64. Turing our data into tensors
69. Loss, optimizer and evaluation functions for classification
76. Creating a straight line dataset
88. Troubleshooting a mutli-class model
95. TorchVision
103. Training and testing loops for batched data
112. Convolutional neural networks (overview)
118. Training our first CNN
126. Introduction to custom datasets
136. Creating image DataLoaders
143. Data augmentation
151. Plotting model 0 loss curves
157. Predicting on custom data