Generative models for generating 3d models?
I was reading about procedural modeling and it made me wonder if anyone has tried getting the data of loads of different 3D models and training a generative classifier on them - so classify all the 3D...
View ArticleClik here to view.
Recursive Neural Networks for Image Segmentation Code? (Socher, Lin, Manning,...
Hi guys, I really want to use this in some current research: http://nlp.stanford.edu/pubs/SocherLinNgManning_ICML2011.pdfit doesn't look like there's any code that will do it for you off the shelf...
View ArticleClik here to view.
Why 'Frankenstein' Robots Could Be the Future of Artificial Intelligence
submitted by CaptainHoek [link][comment]
View ArticleCost increases in each iteration? My implementation of Multinomial Logistic...
Hey guyz, I am trying to implement multinomail logistic regression using gradient descent, following http://ufldl.stanford.edu/wiki/index.php/Softmax_RegressionMy data set has 7 ratings classes from 1...
View ArticleClik here to view.
Hundreds compete to improve machine learning algorithm for $5K prize
submitted by shift_happenz [link][1 comment]
View ArticleDoes something that extracts new information from a paper exist?
This is probably a really hard question, but it would be really cool if something in this direction existed already. When reading a scientific paper, I often end up skimming too quickly over the...
View ArticleMy Attempt at Outperforming Deepmind's Atari Results - UPDATE 6
Hi!Another update!I have been working on the image-to-features system. Deepmind did not have a separate feature extractor and reinforcement learner. They used a convolutional neural network to predict...
View ArticleFor what tasks or kind of data are Random forests based models best suited?
submitted by YesIAmTheMorpheus [link][comment]
View ArticleClik here to view.
Clik here to view.
Clik here to view.
Visualizing MNIST: An Exploration of Dimensionality Reduction
submitted by postit [link][3 comments]
View Articlek-NN: using n-grams instead of LSH/Minhash for nearest neighbor search
Hi I have a newbie question about k-NN search. My understanding is that LSH hashes similar strings/numbers to a same bin with high probability. But wouldn't a character-based n-gram search also perform...
View Articlesklearn vectorizing PoS & numeric data?
If I want to train on text, PoS, and numeric vectors how should this be done? The only thing that made sense so far was to hstack coo_matrix objects. I use CountVectorizer on the PoS tagged text in...
View ArticleJobs in Machine/Statistical Learning for an undergrad?
I'll be finisinish my Bachelors in mathematical statistics next year. I've also done a boat load of free courses on sites like coursera to learn programming. I would love to work with machine learning...
View ArticleYour models in Pylearn2: A tutorial on the minimal effort required to develop...
submitted by dwf [link][comment]
View ArticleHow does the brain do regularization?
I know next to nothing about neuroscience, but I can imagine that the brain needs to perform regularization on it's processes similar to the regularization penalties used in machine learning. Is there...
View ArticleClik here to view.
Hyperparameter search, Bayesian optimization and related topics
submitted by vkhuc [link][1 comment]
View ArticleClik here to view.
Generating n-gram predictors from an existing corpus of text; I could use...
I was having trouble choosing a title that would fit the character limit and adequately describe the problem. My NLP vocabulary is a little limited, so I may be using more words than I need to describe...
View Article