I have a neural network with 2 entry variables, 1 hidden layer with 2 neurons and the output layer with one output neuron. When I start with some randomly (from 0 to 1) generated weights, the network learns the XOR function very fast and good, but in other cases, the network NEVER learns the XOR function! Do you know why this happens and how can I overcome this problem? Could some chaotic behaviour be involved? Thanks!
This is quite normal situation, because error function for multilayer NN is not convex, and optimization converges to local minimum.
You can just keep initial weights that resulted in successful optimization, or run optimizer multiple times starting from different weights, and keep the best solution. Optimization algorithm and learning rate also plays certain role, for example backpropagation with momentum and/or stochastic gradient descent sometimes work better. Also, if you add more neurons, beyond the minimum needed to learn XOR, this also helps.
There exist methodologies designed to find global minimum, such as simulated annealing, but, in practice they are not commonly used for NN optimization, except for some specific cases
Related
I'm trying to navigate an agent in a n*n gridworld domain by using Q-Learning + a feedforward neural network as a q-function approximator. Basically the agent should find the best/shortest way to reach a certain terminal goal position (+10 reward). Every step the agent takes it gets -1 reward. In the gridworld there are also some positions the agent should avoid (-10 reward, terminal states,too).
So far I implemented a Q-learning algorithm, that saves all Q-values in a Q-table and the agent performs well.
In the next step, I want to replace the Q-table by a neural network, trained online after every step of the agent. I tried a feedforward NN with one hidden layer and four outputs, representing the Q-values for the possible actions in the gridworld (north,south,east, west).
As input I used a nxn zero-matrix, that has a "1" at the current positions of the agent.
To reach my goal I tried to solve the problem from the ground up:
Explore the gridworld with standard Q-Learning and use the Q-map as training data for the Network once Q-Learning is finished
--> worked fine
Use Q-Learning and provide the updates of the Q-map as trainingdata
for NN (batchSize = 1)
--> worked good
Replacy the Q-Map completely by the NN. (This is the point, when it gets interesting!)
-> FIRST MAP: 4 x 4
As described above, I have 16 "discrete" Inputs, 4 Output and it works fine with 8 neurons(relu) in the hidden layer (learning rate: 0.05). I used a greedy policy with an epsilon, that reduces from 1 to 0.1 within 60 episodes.
The test scenario is shown here. Performance is compared beetween standard qlearning with q-map and "neural" qlearning (in this case i used 8 neurons and differnt dropOut rates).
To sum it up: Neural Q-learning works good for small grids, also the performance is okay and reliable.
-> Bigger MAP: 10 x 10
Now I tried to use the neural network for bigger maps.
At first I tried this simple case.
In my case the neural net looks as following: 100 input; 4 Outputs; about 30 neurons(relu) in one hidden layer; again I used a decreasing exploring factor for greedy policy; over 200 episodes the learning rate decreases from 0.1 to 0.015 to increase stability.
At frist I had problems with convergence and interpolation between single positions caused by the discrete input vector.
To solve this I added some neighbour positions to the vector with values depending on thier distance to the current position. This improved the learning a lot and the policy got better. Performance with 24 neurons is seen in the picture above.
Summary: the simple case is solved by the network, but only with a lot of parameter tuning (number of neurons, exploration factor, learning rate) and special input transformation.
Now here are my questions/problems I still haven't solved:
(1) My network is able to solve really simple cases and examples in a 10 x 10 map, but it fails as the problem gets a bit more complex. In cases where failing is very likely, the network has no change to find a correct policy.
I'm open minded for any idea that could improve performace in this cases.
(2) Is there a smarter way to transform the input vector for the network? I'm sure that adding the neighboring positons to the input vector on the one hand improve the interpolation of the q-values over the map, but on the other hand makes it harder to train special/important postions to the network. I already tried standard cartesian two-dimensional input (x/y) on an early stage, but failed.
(3) Is there another network type than feedforward network with backpropagation, that generally produces better results with q-function approximation? Have you seen projects, where a FF-nn performs well with bigger maps?
It's known that Q-Learning + a feedforward neural network as a q-function approximator can fail even in simple problems [Boyan & Moore, 1995].
Rich Sutton has a question in the FAQ of his web site related with this.
A possible explanation is the phenomenok known as interference described in [Barreto & Anderson, 2008]:
Interference happens when the update of one state–action pair changes the Q-values of other pairs, possibly in the wrong direction.
Interference is naturally associated with generalization, and also happens in conventional supervised learning. Nevertheless, in the reinforcement learning paradigm its effects tend to be much more harmful. The reason for this is twofold. First, the combination of interference and bootstrapping can easily become unstable, since the updates are no longer strictly local. The convergence proofs for the algorithms derived from (4) and (5) are based on the fact that these operators are contraction mappings, that is, their successive application results in a sequence converging to a fixed point which is the solution for the Bellman equation [14,36]. When using approximators, however, this asymptotic convergence is lost, [...]
Another source of instability is a consequence of the fact that in on-line reinforcement learning the distribution of the incoming data depends on the current policy. Depending on the dynamics of the system, the agent can remain for some time in a region of the state space which is not representative of the entire domain. In this situation, the learning algorithm may allocate excessive resources of the function approximator to represent that region, possibly “forgetting” the previous stored information.
One way to alleviate the interference problem is to use a local function approximator. The more independent each basis function is from each other, the less severe this problem is (in the limit, one has one basis function for each state, which corresponds to the lookup-table case) [86]. A class of local functions that have been widely used for approximation is the radial basis functions (RBFs) [52].
So, in your kind of problem (n*n gridworld), an RBF neural network should produce better results.
References
Boyan, J. A. & Moore, A. W. (1995) Generalization in reinforcement learning: Safely approximating the value function. NIPS-7. San Mateo, CA: Morgan Kaufmann.
André da Motta Salles Barreto & Charles W. Anderson (2008) Restricted gradient-descent algorithm for value-function approximation in reinforcement learning, Artificial Intelligence 172 (2008) 454–482
Having neural network with alot of inputs causes my network problems like
Neural network gets stuck and feed forward calculation always gives output as
1.0 because of the output sum being too big and while doing backpropagation, sum of gradients will be too high what causes the
learning speed to be too dramatic.
Neural network is using tanh as an active function in all layers.
Giving alot of thought, I came up with following solutions:
Initalizing smaller random weight values ( WeightRandom / PreviousLayerNeuronCount )
or
After calculation the sum of either outputs or gradients, dividing the sum with the number of 'neurons in previus layer for output sum' and number of 'neurons in next layer for gradient sum' and then passing sum into activation/derivative function.
I don't feel comfortable with solutions I came up with.
Solution 1. does not solve problem entirely. Possibility of gradient or output sum getting to high is still there. Solution 2. seems to solve the problem but I fear that it completely changes network behavior in a way that it might not solve some problems anymore.
What would you suggest me in this situation, keeping in mind that reducing neuron count in layers is not an option?
Thanks in advance!
General things that affect the output backpropagation include weights and biases of early elections, the number of hidden units, the amount of exercise patterns, and long iterations. As an alternative way, the selection of initial weights and biases there are several algorithms that can be used, one of which is an algorithm Nguyen widrow. You can use it to initialize the weights and biases early, I've tried it and gives good results.
i am experimenting with neural networks. I have a network with 8 input neurons, 5 hidden and 2 output. When i let the network learn with backpropagation, sometimes, it produces worse result between single iterations of training. What can be the cause? It should not be implementation error, because i even tried using implementation from Introduction to Neural Networks for Java and it does exactly the same.
Nothing is wrong. Back propagation is just a gradient optimization, and gradient methods do not have a guarantee of making error smaller in each iteration (you do have a guarantee that there exists a very small step size/learning rate which has such property, but in practise no way of finding it); furthermore you are probably updating weights after each sample making your training stochastic, which is even more "unstable" in this matter (as you do not really calculate the true gradient). However, if due to this, your method is not converging - think about proper scaling of your data as well as reducing the learning rate and probably adding the momentum term. These are just gradient-based optimization-related issues, not BP as such.
I have ran some classification tests in Matlab with feed forward network. Using the standard tansig function the results were better when using more neurons on the hidden layer.
But, when I switched to pure lin I was surprised to see that the results were better when I set a smaller number of neurons on the hidden layer.
Can you help me with an argument for these situation?
The tansig activation function essentially makes it possible than a neuron becomes inactive due to saturation. A linear neuron is always active. Therefore if one linear neuron has bad parameters, it will always affect the outcome of the classification. A higher number of neurons yield a higher probability of bad behavior in this scenario.
Is a genetic algorithm the most efficient way to optimize the number of hidden nodes and the amount of training done on an artificial neural network?
I am coding neural networks using the NNToolbox in Matlab. I am open to any other suggestions of optimization techniques, but I'm most familiar with GA's.
Actually, there are multiple things that you can optimize using GA regarding NN.
You can optimize the structure (number of nodes, layers, activation function etc.).
You can also train using GA, that means setting the weights.
Genetic algorithms will never be the most efficient, but they usually used when you have little clue as to what numbers to use.
For training, you can use other algorithms including backpropagation, nelder-mead etc..
You said you wanted to optimize number hidden nodes, for this, genetic algorithm may be sufficient, although far from "optimal". The space you are searching is probably too small to use genetic algorithms, but they can still work and afaik, they are already implemented in matlab, so no biggie.
What do you mean by optimizing amount of training done? If you mean number of epochs, then that's fine, just remember that training is somehow dependent on starting weights and they are usually random, so the fitness function used for GA won't really be a function.
A good example of neural networks and genetic programming is the NEAT architecture (Neuro-Evolution of Augmenting Topologies). This is a genetic algorithm that finds an optimal topology. It's also known to be good at keeping the number of hidden nodes down.
They also made a game using this called Nero. Quite unique and very amazing tangible results.
Dr. Stanley's homepage:
http://www.cs.ucf.edu/~kstanley/
Here you'll find just about everything NEAT related as he is the one who invented it.
Genetic algorithms can be usefully applied to optimising neural networks, but you have to think a little about what you want to do.
Most "classic" NN training algorithms, such as Back-Propagation, only optimise the weights of the neurons. Genetic algorithms can optimise the weights, but this will typically be inefficient. However, as you were asking, they can optimise the topology of the network and also the parameters for your training algorithm. You'll have to be especially wary of creating networks that are "over-trained" though.
One further technique with a modified genetic algorithms can be useful for overcoming a problem with Back-Propagation. Back-Propagation usually finds local minima, but it finds them accurately and rapidly. Combining a Genetic Algorithm with Back-Propagation, e.g., in a Lamarckian GA, gives the advantages of both. This technique is briefly described during the GAUL tutorial
It is sometimes useful to use a genetic algorithm to train a neural network when your objective function isn't continuous.
I'm not sure whether you should use a genetic algorithm for this.
I suppose the initial solution population for your genetic algorithm would consist of training sets for your neural network (given a specific training method). Usually the initial solution population consists of random solutions to your problem. However, random training sets would not really train your neural network.
The evaluation algorithm for your genetic algorithm would be a weighed average of the amount of training needed, the quality of the neural network in solving a specific problem and the numer of hidden nodes.
So, if you run this, you would get the training set that delivered the best result in terms of neural network quality (= training time, number hidden nodes, problem solving capabilities of the network).
Or are you considering an entirely different approach?
I'm not entirely sure what kind of problem you're working with, but GA sounds like a little bit of overkill here. Depending on the range of parameters you're working with, an exhaustive (or otherwise unintelligent) search may work. Try plotting your NN's performance with respect to number of hidden nodes for a first few values, starting small and jumping by larger and larger increments. In my experience, many NNs plateau in performance surprisingly early; you may be able to get a good picture of what range of hidden node numbers makes the most sense.
The same is often true for NNs' training iterations. More training helps networks up to a point, but soon ceases to have much effect.
In the majority of cases, these NN parameters don't affect performance in a very complex way. Generally, increasing them increases performance for a while but then diminishing returns kick in. GA is not really necessary to find a good value on this kind of simple curve; if the number of hidden nodes (or training iterations) really does cause the performance to fluctuate in a complicated way, then metaheuristics like GA may be apt. But give the brute-force approach a try before taking that route.
I would tend to say that genetic algorithms is a good idea since you can start with a minimal solution and grow the number of neurons. It is very likely that the "quality function" for which you want to find the optimal point is smooth and has only few bumps.
If you have to find this optimal NN frequently I would recommend using optimization algorithms and in your case quasi newton as described in numerical recipes which is optimal for problems where the function is expensive to evaluate.