### Agents with more than one utility function

What would happen if an intelligent agent were programmed with two utility functions which are one the opposite of the other? Would one prevail or will they cancel each other out? Are there studies in this direction?

### Can I provide a CNN with hints?

Let’s say I want to classify a dataset of handwritten digits (CNNs on their own can get 99.7% on the MNIST dataset but let’s pretend they can only get 90% for the sake of this question). Now, I already have some classical computer vision techniques which might be able to give me a clue. For…

### Is traditional machine learning obsolete since neural nets, deep neural nets can always outperform them?

I have been coming across visualizations showing that the neural nets tend to perform better as compared to the traditional machine learning algorithms (Linear regression, Log regression, etc.) Assuming that we have sufficient data to train deep/neural nets, can we ignore the traditional machine learning topics and concentrate more on the neural network architectures? Given…

### Formal proof that every purely reactive agent has behaviorally equivalent standard agent

It kind of makes sense intuitively but I’m not sure about a formal proof. I’ll start with briefly listing definitions from Intro to Multiagent systems, Wooldridge, 2002 and then give you my reasoning attempts thus far. Environment states are defined as $E=(e_{0}, e_{1},…, e_{u})$, agent actions are defined as $Ac=(\alpha_0, \alpha_1, …, \alpha_u)$, an agent’s…

### In neural networks, what does the term depth generally mean?

Is it 1) number of units in a layer 2) number of layers 3) over all complexity of network(1 and 2)

### how to produce documents like factset blackline?

factset blackline reports essentially can compare two 10-Q SEC filings and show you the difference between the two documents. It highlights added items in green and removed items in red + strikethrough. (essentially its a document diff. but longer term i would like to run algorithms on the diffs) i dont care to change colors…

### How do I poison an SVM with manifold regularization?

I’m working on Adversarial Machine Learning, and have read multiple papers on this topic, some of them are mentioned as follows: Poisoning Attacks on SVMs: https://arxiv.org/pdf/1206.6389.pdf Adversarial Label Flips on Support Vector Machines However, I am not able to find any literature on data poisoning for Manifold regularization. Is there anyone who has knowledge about…

### Is the minimax algorithm model-based?

Trying to get my head around model-free and model-based algorithms in RL. In my research, I’ve seen the search trees created via the minimax algorithm. I presume these trees can only be created with a model-based Agent which knows the full environment/rules of the game (if it’s a game…)? If not, could you explain to…

### Understanding V- and Q-functions

Assume the existence of a Markov Decision Process consisting of: State space $S$ Action space $A$ Transition model $T: S \times A \times S \to [0,1]$ Reward function $T: S \times A \times S \to \mathbb{R}$ Distribution of initial state $p_0: S \to [0,1]$ and a policy $\pi:S\to A$. The V- and Q-functions take expectations…

### Can neural style transfer work on the image style in this question or is there a better technique?

I’ve been working with this neural style paper https://arxiv.org/pdf/1508.06576v2.pdf to try and transfer the style from this image to photos of pets. In case you’re not familiar with the technique, I’ll leave a brief explanation of it at the end. After taking the time to understand some of the concepts in the paper I’ve come…