Hacker News Reader

Comment by Fede_V | Hacker News Reader

Sure.

Random forests are a very powerful machine learning method that has proven to give excellent performance with very little tuning. Neural networks with many layers (aka deep learning) is the new frontier of machine learning - they are very powerful but require extensive tuning (the architecture of the network) and lots of examples before they become practical.

In this paper, the authors combine the two methods - they basically stack a random forest on top of a neural network, and obtain some cutting edge results. One of the main theoretical results in the paper is that they propose a differentiable (which means you can use gradient-based optimization techniques) technique to optimize the parameters of the trees (which are the building blocks of the random forest).

View on HN

I think there are a few additional important details.

It's not so much that they stack a random forest on top of a neural network, as that they are trying to train neural networks that have tree-like properties. Deep neural networks can be expensive to evaluate because every layer is needed to compute the resulting label. On the other hand, in a decision tree you only need to evaluate one of a nodes children (i.e., evaluation is linear in the depth of the tree).

They combine these ideas by allowing some nodes in the network to branch (so for a given image, you choose one of two neural networks to evaluate). These nodes don't have to occur at the top level, but can occur in the middle of the network as well.

The difficulty is how you train these nodes; that's where the differential technique for optimizing trees come in. Because you have a unified training algorithm, you can mix and match tree-like nodes and neural network like nodes and train the whole thing.

All in all, the hope is that getting a label for a given node is much faster, so you can run these on smaller devices such as phones without sacrificing accuracy.

Also, it might be worth adding that random forests are based on decision trees, which can be interpreted by humans.

While it's hard to interpret a random forest, it's still much more interpretable than a neural network. Maybe this model is also easier to interpret by humans.

Random forests are very difficult to interpret especially once you start having lots of trees.

>While it's hard to interpret a random forest, it's still much more interpretable than a neural network

Depends on the domain. The first layer or two of a neural network can be fairly interpretable on image or spectrogram (sound) data, for example.

New frontier? They've been popular for over 20 years.

That's AI. Every generation invents everything again. Probably works this way in other fields too.

(Yes this is hyperbole, but any old timers out there will know the feeling)

> That's AI. Every generation invents everything again.

Also "Past decades was AI winter. But no worries, now we'll start seeing human intelligence in a about next year" probably heard that since late 90's.

They really came to the forefront with alex.net - GPUs plus lots of labeled examples made them suddenly very practical.

Yes and No. Layer to layer training of deep belief nets were doing very well before alex.net came along, although alex.net was seminal for images. People often miss the big 'advances' in RNN's, although those go back to the 90's and earlier. A lot of this (but not all) is also due to more data, better and faster hardware (including GPU's). Although there have been some important algorithmic enhancements too.

Regular neural networks were popular until they stopped delivering best-in-class results for a lot of problems.

Recent hardware made it possible to train more layers and they're now getting cutting-edge results in many areas again so they're now getting more attention again.

Old time neural networks not even came close to current models in terms of performance.

I clearly remember in my machine learning class, one professor mentions neural networks and says it is slow and impossible to tame when the layers goes up thus loses its popularity. That is just 3-4 years ago.

I took some machine learning classes a while 1-2 years ago at the TU Berlin, and while there was some emphasis on neural nets, it was just as much emphasis on SVMs, with the remainder of the time filled with other traditional models. The lecturer had done some research into SVMs, though, so it was probably just bias rather than old-fashionedness. He was also of the mathematical sort, and I suspect the unanalyzable nature of NNs rubbed him the wrong way. I'm not saying that all other AI/ML methods should be abandoned, but NN definitely didn't get the attention it deserved. Deep learning techniques weren't covered at all, for example.

Deep learning has really only recently become successful with new learning algorithms such as constrastive divergence and convolutional neural networks. Previous efforts were focused around backpropagation, but due to the signal loss across many layers there was never enough information in the output layer to successfully train the network.

Time for a fact update! My, my, how time flies.

Deep learning has really only recently become successful

hinton coined the term "deep learning" around 2006/2007 (more around deep belief nets/RBMs, but still, same thing), if that's considered "recently."

constrastive divergence and convolutional neural networks.

CD was also ~10 years ago. CNNs were reading your checks and postal zipcodes in the mid 90s.

successfully train the network.

In the early 90s, RNNs were driving cars on highways using only webcams under basically VFR. No giant sensors, no LIDAR, no GPS, no mesh networks, just camera input.

Is this Jurgen? :)

The 2012 ImageNet results were what really launched the current interest.

Before that there was little evidence that any form of neural network was massively better than other forms of machine learning. Now it has become clear that isn't the case.

>> One of the main theoretical results in the paper is that they propose a differentiable .. technique to optimize the parameters of the trees.

Yay! Now Decision Trees too can get stuck in local optima! :D

(totally tongue in cheek)

Even though this is tongue-in-cheek, it makes no sense. Decision trees are traditionally trained in a greedy, non-globally-optimal fashion.

What I mean is that decision trees are not seen as optimising a function so it doesn't make much sense to think of them as finding optima, or getting stuck in sub-optima (if I may).

That's the traditional view. I guess it's always possible to see decision trees as optimising a binary function, but that's probably to be filed under "original research". Or maybe not- I'm not sure.

In any case, I've never heard of anyone worried that a tree learner would get stuck anywhere. The concern is usually with overfitting.

Reply on news.ycombinator.com