### Confusion on CNN filter layer depth and filter restrictions

I am a bit confused on the layer depth of later convolutional filters. At layer 1 there are usually 40 or so 3x3x3 filters. Each of these filters outputs a 2d array so the total output of the first layer is 40 2d arrays. Does the next convolutional filter have a depth of 40? So…

### How would I go about performing a single step of fradient descent on this model?

I have classification model which consists of a CNN followed by an SVM. I used the keras library for the CNN portion and sklearn for the SVM portion. I am assuming I will have to fiddle with the weights and perform a partial derivation at each of the layers to find the derivative in terms…

### How can a new metric applied for humans causing danger on railtracks?

I am writing myself and was thinking about, what kind of metric can be applied to measure the “dangerousness” of a human being on a railtrack? For example detecting if a human is running on the rails? Maybe predicting the human movement towards rails, the distance to the vehicle (ego perspective) or something else?

### In machine learning, how can we overcome the restrictive nature of conjunctive space?

In machine learning, problem space can be represented through concept space, instance space version space and hypothesis space. These problem spaces used the conjunctive space and are very restrictive one and also in the above-mentioned representations of problem spaces, it is not sure that the true concept lies within conjunctive space. So, let’s say, if…

### Why are the terms classification and prediction used as synonyms in the context of deep learning?

Why are the terms classification an prediction used as synonyms especially when it comes to deep learning? E.g.: a cnn predicts the handwritten digit. To me prediction is telling the next step in a sequence. whereas classification is to put labels on (a finite set of) data.

### Reinforcement Learning Continuous Control (DDPG): How to avoid thrashing of issued actions? How to reward smooth output over flittering?

Currently I’m working on a continuous state / continuous action controller. It shall control a certain roll angle of an aircraft by issuing the correct aileron commands (between -1…1 continuous). To this end I use a neural network and the DDPG algorithm which shows promising results after som 20 minutes of training. I stripped down…

### Reinforcement Learning Continuous Control (DDPG): How to avoid thrashing of issued actions? How to reward smooth output over flittering?

Currently I’m working on a continuous state / continuous action controller. It shall control a certain roll angle of an aircraft by issuing the correct aileron commands (between -1…1 continuous). To this end I use a neural network and the DDPG algorithm which shows promising results after som 20 minutes of training. I stripped down…

### Reinforcement Learning Continuous Control (DDPG): How to avoid thrashing of issued actions? How to reward smooth output over flittering?

Currently I’m working on a continuous state / continuous action controller. It shall control a certain roll angle of an aircraft by issuing the correct aileron commands (between -1…1 continuous). To this end I use a neural network and the DDPG algorithm which shows promising results after som 20 minutes of training. I stripped down…

### Why is my model accuracy high in train-test split but actually worse than chance in validation set?

I have trained a XGboost model to predict survival for the Kaggle Titanic ML competition. As with all Kaggle competitions there is a train dataset with the target variable included and a test dataset without the target variable which is used by Kaggle to compute the final accuracy score that determines your leaderboard ranking. My…

### Is a neuronal network able to optimize itself for speed?

I am experimenting with OpenAI Gym and reinforcement learning. As far as I understood, the environment is waiting for the agent to make a decision, so it’s a sequential operation like this: decision = agent.decide(state) state, reward, done = environment.act(decision) agent.train(state, reward) Doing it in this sequential way, the Markov property is fulfilled: the new…