When looking at the performance, it doesn't seem like the LSTM adds very much compared to simpler multi-layer perceptrons. I wonder if that is because temporal information isn't very useful or because the LSTM wasn't capable of learning some of the more complicated temporal patterns.
I would love to play around with the data, unfortunately, I assume it's private (for good reason) due to potentially sensitive patient data.
If anyone is interested in related methods for time series, I just put up code for our recent action segmentation paper using Temporal Convolutional Networks (https://github.com/colincsl/TemporalConvolutionalNetworks). I would be very interested in trying this model on the ICU data. In my experience, TCNs are much better at learning complex temporal pattern than LSTMs.
For those interested in learning vision from a machine learning perspective I would suggest "Computer Vision: Models, Learning, and Inference" [1]. Szelinski's book is also great but gives a more classical overview of computer vision.
They are implying that medical devices are notoriously bad at being proprietary/closed. Hospitals would be much better off if the devices could talk to each other but it isn't feasible as-is because device manufacturers want lock-in. The current situation leads to issues like alarm fatigue where nurses effectively ignore problems due to too many devices. If they were centralized then there could be one management system that intelligently alerts the nurse of any issues.
I used to (almost) exclusively use Python and didn't like that I had to go bath and forth with Cython to make my models fast. Earlier this year I ported some of my code to Julia and feel more productive because of it. I feel like it's easier for me to implement new non-trivial improvements to my models than it was before.
For what it's worth I still stick with Python for computer vision applications. I mostly use Julia for timeseries models (e.g. Semi Markov CRFs) where it's harder to vectorize everything.
If I were restart again I'm not sure if I would suggest going the Julia route. I know there are alternatives like Numba that enable you write efficient code with minimal effort. Overall I like Julia as a language but there are a lot of little issues due to it being a new language.
You're right that the video looks very impressive. However, I'm hesitant to believe that this actually works as well as one might perceive. In this area (called semantic segmentation in the computer vision world) it is common for a people to highlight both the good cases (where the labels/segmentation are correct) and the bad cases (where they are incorrect). In the MS video they only show the good. It's easy to cherry-pick examples where it works -- even if the overall accuracy is very low.
Furthermore, I don't know which dataset they're using. Perhaps it only works on a small set of objects such as those shown in the video.
I don't mean to knock their results but it will still take time to get this to work on a more broad set of videos.
I've only been watching from the Deep Learning sidelines -- but I believe people have steered away from pretraining over the past year or two. I think on practical datasets it doesn't seem to help.
As a robotics/computer vision researcher I disagree with you. The first Kinect was a godsend for robotics - previously it cost thousands of dollars for similar types of sensors. Typically we just want the raw data so that we can do whatever processing we want. It was nice because it worked on Mac/Linux/Windows without too much hassle. The new Kinect on the other hand is of little use to me right now. It's locked down on Windows - and as far as I know you need the special dev kit version for it to even work.
Also, a "cheap camcorder" is nothing compared to this. The Kinect is a 3D sensor. You would need 2 "cheap camcorders," stereo vision algorithms/hardware to process it in real-time, and even then the quality typically wouldn't be as good as the Kinect.
Tangentially, it's also disheartening (at least for the time being) that Apple recently bought Primesense - the maker of the original Kinect. Primesense was selling a better 3D sensor for developers/researchers. Apple shut it down as soon as they bought them.
In Europe you typically need a masters degree before you start a PhD program. In the US you don't - you can think of it as a 2+3 type program where you spend the first couple of years taking classes (and getting your masters) and the next three doing your thesis.
I am surprised that there is no mention of this in the course syllabus -- in fact it looks like a lot of recent techniques that are missing. They don't even talking about LSA(/SVD)-based methods until the end of the course.
I'm not sure about the MCAT/GMAT/LSAT but the GRE is a pretty bad indicator. For example, everyone who goes to grad school for computer science or engineering gets minimum a 750 on the quantitative section. The math only tests high school level ability.
While I don't have any links, I think that there are many studies showing that SAT/GRE type scores don't mean very much.
Me and many of the people I know use it everyday. It's the easiest 'cloud' storage out there and certainly the most popular. I'm not sure why you say it has no place in the future.
I don't think vision/ML techniques will be a viable option for quite a while. These algorithms have a hard enough time correctly classifying dozens of classes, let alone 8.7 million species of animals. This is especially true given that many of these species only have a small number of images.
I'm living in Germany for the summer and am surprised at how little people use cards here compared to the in the states. I love being able to use a debit/credit card so that everything I buy is logged. That means I can see everything (automatically tagged) using Mint. It also decreases the hassel of carrying as much cash around and going to the ATM as often.
On a tangent, it seems like people here have more of a negative view on credit cards - as if they assume you only use one if you can't actually pay. As long as you pay off your bill each month there is no real downside for the customer.
I would love to play around with the data, unfortunately, I assume it's private (for good reason) due to potentially sensitive patient data.
If anyone is interested in related methods for time series, I just put up code for our recent action segmentation paper using Temporal Convolutional Networks (https://github.com/colincsl/TemporalConvolutionalNetworks). I would be very interested in trying this model on the ICU data. In my experience, TCNs are much better at learning complex temporal pattern than LSTMs.