# Tag Info

1

Is there any role of convex optimization in AI? Yes, of course! If so, in what algorithms or problem settings or systems? The problem of finding the parameters of a support vector machine can be formulated as a convex optimization problem. Another example is linear regression. See also the paper Convex Optimization: Algorithms and Complexity (2014) by ...

1

Full disclosure: I work at Dessa, the company that developed this tech. We built a machine learning experiment management tool, called Atlas. The main feature is experiment management, allowing you to run thousands of experiments concurrently. This might help with your problem above https://github.com/dessa-oss

0

Besides the last layer rest of the weights are shared among all classes. When an image is passed to the network all weights are updated accordingly. The only weights that are directly responsible for one specific class are the ones of the final layer. The rest of the weights are updated to find the best values to minimize the average loss for all classes. ...

1

The main thing to keep in mind when designing a reinforcement learning agent is that you need to develop an interactive environment in which the agent can learn and define the possible moves the agent can make. In your case, the environment is the memory cards. Next you need to define how the agent can interact with the environment, that is choosing a card ...

3

The most common way people deal with inputs of varying length is padding. You first define the desired sequence length, i.e. the input length you want your model yo have. Then any sequences with a shorter length than this are padded either with zeros or with special characters so that they reach the desired length. If an input is larger than your desired ...

0

I found a paper that gives a table of time complexities for different architectures using linear programming-based training: https://arxiv.org/abs/1810.03218

0

(All notations based on Understanding ML: From Theory to Algorithms) The layman's term for NFL is super misleading. The comparison between PAC learnability and NFL is kind of baseless since both proof's are built on a different set of assumptions. Let's review the definition of PAC learnability: A hypothesis class $H$ is PAC learnable if there exist a ...

2

There is actually a github project about 'solving' Nim that implements certain type of Q-learning reinforcement algorithm (described in undergraduate thesis of Erik Jarleberg (Royal Institute of Technology) entitled "Reinforcement learning on the combinatorial game of Nim") that supposedly finds that optimal strategy lying down there inside in the game that ...

2

In neural networks, the family of functions and the shapes that they can make for decision surfaces is determined by the activation function you use (in your case, tanh or hyperbolic tangent). Assuming at least one hidden layer, then the universal approximation theorem applies. How closely you can approximate any given function is limited by the number of ...

0

If the noise is confined to a particular spectral band, Fourier transform followed by filtering, followed by an inverse Fourier transform will work. If it is multiplicative noise, filtering the Fourier transform of the logarithm of the signal might work. Really, the nature of the noise determines what's possible and the best way to remove it.

1

This sounds to me like a use case for a chatbot. You would have different intents reflecting the types of user queries that your system can respond to. The intent matching can be done by pattern matching, machine learning (classification), or a combination of the two (hybrid). You can then use the chatbot to ask clarification questions or elicit more ...

0

From my point of view the answer of your questions can be solved by looking further at the Generative Adversarial Networks. Generative adversarial networks (GANs) are algorithmic architectures that use two neural networks, pitting one against the other (thus the “adversarial”) in order to generate new, synthetic instances of data that can pass for real data....

3

Dialogue is a hard problem because it requires pretty advanced cognitive functions. Leaving aside all the lower levels of language analysis (phonology if dealing with speech, morphology and syntax), you quickly run into interpretation problems that require a lot of world knowledge. Simple question and answer is fine, and restricted domains are somewhat ...

1

First of all, I am not very familiar with details of NLP and NLU systems and concepts, so I will provide an answer based on the slides entitled Natural language understanding in dialogue systems (2013) by David DeVaul, a researcher on the topic. A dialogue system is composed of different parts or modules. Here's a diagram of an example of a dialogue system. ...

2

The main distinction between tasks is 'classification' vs 'regression'. In classification you would try to identify the presence of a cloud or not in an image, if you want to predict the level of 'cloudness' with continuous values you are then performing a regression task. I'm not aware about state-of-the models specific for images, but you can potentially ...

0

I don't think this classify as an NLP problem, there is almost no semantic analysis needed, it is more like a classification problem using categorical features. NLTK is surely valuable if you want to perform some text 'cleaning' or preprocessing before encoding the variables. The only NLP application that I think you could apply here is some sentiment ...

0

You should at least crop the plots and add a legend. Maybe also provide some scores (accuracy, auc, whatever you're using). Anyway, it doesn't look your model is underfitting, if it was you should have high error at both, training and test phase and the lines would not cross.

3

According to Wikipedia: A statistical model is a mathematical model that embodies a set of statistical assumptions concerning the generation of sample data (and similar data from a larger population). A statistical model represents, often in considerably idealized form, the data-generating process. Answer to your question: To build any neural network ...

1

You can try image captioning. You can train a CNN model for image, and then, on top of that, provide the model embedding to another LSTM model to learn the encoded characteristics. You can directly use the pre-trained VGG-16 model and use the second last layer to create your image embeddings. Show and Tell: A Neural Image Caption Generator is a really nice ...

0

The original graph for the aforementioned Bayesian Optimisation is similar to the graph in these slides (slide 18) along with the calculations. So, according to the tutorial the graph shown should actually have the term $p(D|m)$ on the y-axis, thus making it a generative model.Now the graph starts to make sense, since a model with low complexity cannot ...

3

Yes, PAC learning can be relevant in practice. There's an area of research that combines PAC learning and Bayesian learning that is called PAC-Bayesian (or PAC-Bayes) learning, where the goal is to find PAC-like bounds for Bayesian estimators. For example, Theorem 1 (McAllester’s bound) of the paper A primer on PAC-Bayesian learning (2019) by Benjamin ...

1

You can use image captioning. Look at the article Captioning Images with CNN and RNN, using PyTorch. The idea is very profound. The model encodes the image to high dimensional space and then passes it through LSTM cells and LSTM cells produce linguistic output. See also Image captioning with visual attention.

2

The term you are looking for is multi-label classification, i.e. where you are making more than one classification on each image (one for each label). Most examples you'll find online are in the NLP domain but it is just as easy with CNNs since it's essentially defined by the structure of the output layer and the loss function used. It's not as complicated ...

0

The paper (or report) that formally introduced the perceptron is The Perceptron — A Perceiving and Recognizing Automaton (1957) by Frank Rosenblatt. If you read the first page of this paper, you can immediately understand that's the case. In particular, at some point (page 2, which corresponds to page 5 of the pdf), he writes Recent theoretical studies by ...

0

I would do as suggested in the comments. First select an encoding scheme. I think what is called a difference hash would work well for this application. Code for that is shown below. Now take your data set of images and run them through the encoder and save the result in a database. The database would contain the "labeling" text and the encoder result. Now ...

0

From what you wrote, the problem sounds a bit like face recognition, where a camera takes a picture of your face and compares it with a bunch of pictures in a database, for example, one for each employee if its at a company's main gate. If you look "similar" to one of the pictures in the database, the door opens and your ID/Name is displayed on a terminal. ...

1

I do not know how you will apply your data to the techniques I'll give you some brief overview of techniques used in time series prediction: Extended Kalman Filtering: This is a kind of control system approach and is generally used to control trajectory of missiles. Here is a question (based on an EKF paper) in our stack on this topic. You can check the ...

1

Things like this a really hot topic in research right now, and it's very difficult to get high accuracy on a chaotic system like the stock market. That being said, I would probably recommend preprocessing your data rather than having your primary neural network decide what to accept and what not to. For example, in your specific case, you could model a ...

1

Have a look at the paper A Modular Architecture for Unsupervised Sarcasm Generation (2019) by Mishra et al. In the abstract, the authors write In this paper, we propose a novel framework for sarcasm generation; the system takes a literal negative opinion as input and translates it into a sarcastic version. Our framework does not require any paired data ...

1

I think, one could generate a data set, with a random variable in each component of the data vector, add this data to the training data set, and then shuffle the combined data set.

0

If you don't manually enter in the information, you expect a system to. Which becomes circular since you're trying to teach a system to detect images....

0

The book has actually proven the theorem rigorously in Chapter 2. I don't want to prove it here, but you can look it up. I will try to explain parts which are non obvious (and somewhat confusing according to the book's literature). So for PAC learning (with or without the realizability assumption) the theory is that given a data-set of size: m \geq [\...

0

Tbh I think stock prices are essentially impossible to predict as you're not taking into account the data from outside the stock market. I'd argue any successful model would need to be trained on news, consumer sentiment, etc etc. The only ones which maybe work are HFT.

3

The sentences coming from the same document, author, etc., are unlikely to be independent, that is, the occurrence of a sentence $s_i$ in a certain document $d$ is likely correlated with the occurrence of another sentence $s_j$. If they are not independent, they can also not be independent and identically distributed (which is a stronger condition). The same ...

1

You can find the dataset in the following links: Pomegranate Disease Detection Using Image Processing fruits 360 datasets

1

I developed a python script to crop faces using MTCNN. I found this to be the most accurate of all the face cropping algorithms at the expense of being somewhat slower. The function I developed is on the kaggle website at https://www.kaggle.com/gpiosenka/detect-align-resize-rename-facial-images. The markup first cell explains how to use it. In a nutshell ...

1

Running for "to many" epochs can indeed lead to over fitting. You should look at the validation loss. If on AVERAGE it continues to decrease then you are not yet over fitting. You may be tempted to run more epochs in hopes your loss will decrease but unless you adjust your learning rate dynamically at some point you won't get any improvement. If you use ...

1

Training a neural network for "too many" epochs than needed without using early stopping criterion leads to overfitting, where your model's ability to generalize decreases.

1

Rather than providing a rule of thumb (which can be misleading, so I am not a big fan of them), I will provide some theoretical results (the first one is also reported in paper How many hidden layers and nodes?), from which you may be able to derive your rules of thumb, depending on your problem, etc. I will be updating this answer, as I find more ...

1

First of all, I would like to say that it is possible that these terms are used inconsistently, given that at least transfer learning, AFAIK, is a relatively new expression, so, the general trick is to take terminology, notation and definitions with a grain of salt. However, in this case, although it may sound confusing to you, all of the current ...

Top 50 recent answers are included