Udacity and Baidu partners up to teach autonomous vehicle driving and engineering fundamentals for FREE! This course will center around Baidu's free open source Apollo self-driving car framework.
Normally Udacity nanodegrees and courses cost north of $599 at launch, $200 per month or even $2000+ for the entire nanodegree. This free course is an amazing news for all learn to coders.
The course is launching soon, sign up and be notified https://www.udacity.com/apollo
https://blog.udacity.com/2018/01/udacity-baidu-announce-self-driving-car-partnership-ces.html
https://blog.udacity.com/2018/01/udacity-baidu-announce-self-driving-car-partnership-ces.html
Monday, July 16, 2018
Tuesday, June 26, 2018
Recurrent Neural Network RNN Basics
Recurrent Neural Network (RNN) is useful for processing sequence data like sound, words, and time series data . RNN remembers a bit of the state from before. It can predict what will come next. Time series is good for heart disease over time, hormone level, blood sugar.
RNN weakness: sometimes gradients too close to 0 or too computationally large. It can also be bad at tracking long term memories - need to use LSTM instead, which has a forget gate, input gate, update layer, output layer
Transform sequences like text, music, time series data,
Build a RNN generate new text character by character
Natural language processing, Word embedding, Word2Vec model, Semantic relationship between words,
Combine embedding and RNN to predict sentiment of movie reviews
Hyperparameters in RNN
Hyperparameters are values that we need to set prior to applying an algorithm. Example: learning rate, mini batch size, epochs. There's no magical number. The optimal value depends on the task on hand.
Hyperparameter concepts: starting values, intuitions
Two main types of hyperparameters optimizer hyperparameters and model hyperparameters. Optimizer hyperparameters related to the optimization and training process more than the model itself. Learning rate, mini batch size, number of training iterations are optimizer hyperparameters. Model hyperparameters are variables that relate to the structure of a model. Examples include number of hidden units, number of layers, and model specific hyperparameters.
Yoshua Bengio: learning rate is the most important hyperparameter. Good starting point = 0.01. Also frequently seen: 0.1, 0.01, 0.001, 0.00001, 0.000001
Intuition for starting small (important): If our learning rate is perfect - the multiplier is the best, then in rare ideal scenario we will land at the optimal point. Any learning rate smaller than the perfect rate, will still converge, and would not overshot the optimal point. If learning rate is too large, will never converge (if it is more than twice the optimal rate for example. If it is close enough to the ideal rate, it may still converge. ). Intuition that is must start small. Udacity Deep Learning Nanodegree Part 5 RNN Hyperparameter No.3 Learning Rate gives a great visual illustration.
If learning rate is too small, may take too long to converge, wasting valuable computing resources.
Yoshua Bengio: learning rate is the most important hyperparameter. Good starting point = 0.01. Also frequently seen: 0.1, 0.01, 0.001, 0.00001, 0.000001
Intuition for starting small (important): If our learning rate is perfect - the multiplier is the best, then in rare ideal scenario we will land at the optimal point. Any learning rate smaller than the perfect rate, will still converge, and would not overshot the optimal point. If learning rate is too large, will never converge (if it is more than twice the optimal rate for example. If it is close enough to the ideal rate, it may still converge. ). Intuition that is must start small. Udacity Deep Learning Nanodegree Part 5 RNN Hyperparameter No.3 Learning Rate gives a great visual illustration.
If learning rate is too small, may take too long to converge, wasting valuable computing resources.
Machine Learning and Deep Learning for Health Care
Two frequently used models are Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). Both are useful for recognizing structures in data.
Convolutional Neural Network (CNN) is useful for image recognition in medical imaging, diagnosis based on medical imaging, tumor diagnosis. Recurrent Neural Network is the less obvious one. It is useful for processing sequence data like sound, words, and time series data - understanding what will come next. Time series is good for heart disease over time, hormone level, blood sugar
Machine Learning for Radiology
The paper Implementing Machine Learning in Radiology Practice and Research (Kohli et al.) concluded that Machine Learning will assist radiologist rather than replacing their jobs. However, Geoff Hinton, a leader in Machine Learning, Deep Learning and Artificial Intelligence, thinks there's no question radiologist will be replaced https://www.youtube.com/watch?v=2HMPRXstSvQ.
Convolutional Neural Network (CNN) is useful for image recognition in medical imaging, diagnosis based on medical imaging, tumor diagnosis. Recurrent Neural Network is the less obvious one. It is useful for processing sequence data like sound, words, and time series data - understanding what will come next. Time series is good for heart disease over time, hormone level, blood sugar
Machine Learning for Radiology
The paper Implementing Machine Learning in Radiology Practice and Research (Kohli et al.) concluded that Machine Learning will assist radiologist rather than replacing their jobs. However, Geoff Hinton, a leader in Machine Learning, Deep Learning and Artificial Intelligence, thinks there's no question radiologist will be replaced https://www.youtube.com/watch?v=2HMPRXstSvQ.
Image Processing using coding
This section is related to Convolutional Neural Networks CNN. These filters are also known as a kernel - a function that can change the original image.
Image processing - blurring filter: for each pixel, take a weighted pixel average of the pixels around it.
Image processing - edge detection, contrast: take differences of the pixels, detect horizontal lines or vertical lines by taking differences using positive and negative numbers.
There are other kernels that take variation of averages pixels.
One famous filter is called Sobel Filter
Image processing - blurring filter: for each pixel, take a weighted pixel average of the pixels around it.
Image processing - edge detection, contrast: take differences of the pixels, detect horizontal lines or vertical lines by taking differences using positive and negative numbers.
There are other kernels that take variation of averages pixels.
One famous filter is called Sobel Filter
Convolutional Neural Network
Pixel illumination are the features, the input data, in CNN models.
CNN helps figure out what kernels, filters, and features to detect all the way backwards using a process called back propagation.
Back propagation is Neural Networks' way to update weights as in Gradient Descent. Back propagation starts from the correct answer, update the weights backwards layer by layer until the final classifications become more correct.
Don't have to see the entire shape. Should be able to recognize partial shapes, obstructed views. For example, a half hidden cow is still a cow.
Should be able to recognize different styles. Van Gough's portrait in post-impressionist style is still Van Gough. It does not change the identity or the classification of the image.
CNN helps figure out what kernels, filters, and features to detect all the way backwards using a process called back propagation.
Back propagation is Neural Networks' way to update weights as in Gradient Descent. Back propagation starts from the correct answer, update the weights backwards layer by layer until the final classifications become more correct.
Don't have to see the entire shape. Should be able to recognize partial shapes, obstructed views. For example, a half hidden cow is still a cow.
Should be able to recognize different styles. Van Gough's portrait in post-impressionist style is still Van Gough. It does not change the identity or the classification of the image.
Monday, June 25, 2018
Udacity nanodegree syllabus program length and projects
Computer Vision
+ 3-Month Program
+ 3 Reviewed Projects
+ 3 Courses
Robotics Software Engineer
+ 4-Month Term
+ 4 Reviewed Projects
+ 6 Courses
Intro to Self-Driving Cars
+ 4-Month Program
+ 7 Reviewed Projects
+ 7 Courses
Flying Car
+ 3-Month Term
+ 4 Reviewed Projects
+ 4 Courses
Caution most new udacity nanodegrees require multiple terms. You may have to spend $2000 per program.
+ 3-Month Program
+ 3 Reviewed Projects
+ 3 Courses
Robotics Software Engineer
+ 4-Month Term
+ 4 Reviewed Projects
+ 6 Courses
Intro to Self-Driving Cars
+ 4-Month Program
+ 7 Reviewed Projects
+ 7 Courses
Flying Car
+ 3-Month Term
+ 4 Reviewed Projects
+ 4 Courses
Caution most new udacity nanodegrees require multiple terms. You may have to spend $2000 per program.
Thursday, June 21, 2018
Udacity Launches Blockchain Nanodegree
Wow Udacity really knows how to capitalize on the hype: just announced the blockchain nanodegree!
Visit Uadacity blockchain developer nanodegree now.
What to watch out for? Udacity tends to be experimental. Being in the first class may mean better price tag, but potentially extremely hard-to-follow incoherent content. I definitely had the issue with Machine Learning nanodegree when it first came out.
It does seem like one of those startup prototypes: standard format, basic content, with some industry professionals supporting the course including: Coinbase, factom, madhive.
Definitely worth it if your company pays the bill. Otherwise, wait and see better results.
 |
| Udacity Blockchain Developer |
What to watch out for? Udacity tends to be experimental. Being in the first class may mean better price tag, but potentially extremely hard-to-follow incoherent content. I definitely had the issue with Machine Learning nanodegree when it first came out.
It does seem like one of those startup prototypes: standard format, basic content, with some industry professionals supporting the course including: Coinbase, factom, madhive.
Definitely worth it if your company pays the bill. Otherwise, wait and see better results.
Subscribe to:
Posts (Atom)
-
Can hack schools solve Silicon Valley's talent crunch? The truth about coding bootcamps and the students left behind http://t.co/xXNfqN...
-
The bogus request from P2PU to hunt for HTML tags in real life has yielded a lot of good thoughts. My first impression was that this is stup... -
This review is updated continuously throughout the program. Yay I just joined the Udacity Nanodegree for Digital Marketing! I am such an Uda...