Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange
Join us in building a kind, collaborative learning community via our updated Code of Conduct.

Deep learning is a branch of machine learning that uses neural networks with many layers to allow modeling of high-level abstractions.

0
votes
0answers
6 views

A book that cover both theory and practice for an engineer

This might be a boring question. After reading many Quora questions about this matter it seems that books on AI/ML are too deep or too theoretical. They can be books for people who only talk about AI ...
1
vote
0answers
13 views

How to use Cross Entropy loss in pytorch for binary prediction? [migrated]

In the pytorch docs, it says for cross entropy loss: input has to be a Tensor of size (minibatch, C) Does this mean that for binary (0,1) prediction, the input must be converted into an (N,2) ...
2
votes
2answers
49 views

How can I train model to extract custom entities from text?

I have a 100-150 words text and I want to extract particular information like location, product type, dates, specifications and price. Suppose if I arrange a training data which has a text as input ...
4
votes
0answers
42 views

Is topological sophistication necessary to the furtherance of AI?

The current machine learning trend is interpreted by some who are new in the disciplines of AI as meaning that orthogonal structures like ANNs, CNNs, and RNNs can exhibit human intelligence. It is ...
2
votes
0answers
41 views

Loss function for Hierarchical Multi-label classification

I am looking to try different loss functions for a hierarchical multi-label classification problem. So far, I have been training different models or submodels like multilayer perceptron ( MLP )branch ...
1
vote
0answers
26 views

How recurrent neural network work when predict many days?

I use recurrent neural network, RNNs have to get input one value per step and it will show one value output. If I have daily sale demand time series data. I want to predict sale demand for three ...
3
votes
0answers
22 views

How should continuous action/gesture recognition be performed differently than isolated action recognition

I am going to train a deep learning model to classify hand gestures in video. Since the person will be taking up nearly the entire width/height of the video and I will be classifying what hand gesture ...
2
votes
2answers
39 views

Reinforcement Learning Batch Size

I am using a neural network as my function approximator for reinforcement learning. In order to get it to train well I need to choose a good learning rate. Hand picking one is difficult, so I read up ...
3
votes
1answer
42 views

Why coupling coefficients (c) in Capsule networks can't by learned by backpropagation?

The paper Dynamic Routing Between Capsules uses the algorithm called "Dynamic Routing Between Capsules" to determine the coupling coefficients between capsules. Why it can't be done by ...
6
votes
2answers
258 views

Can deep networks be trained to prove theorems?

Assume we have a large number of proofs in first order predicate calculus. Assume we also have the axioms, corollaries, and theorems in that area of mathematics in that form too. Consider the each ...
4
votes
2answers
53 views

Image Classification

I am currently working on a project to classify snake types separately using an image of the snake. I need to train a module to classify snake images, but the problem is there are only a small number ...
0
votes
0answers
12 views

Deep learning with sparse input features

I training a generative adversarial network (GAN) to generate images given edge histogram descriptor (EHD) features of the image. The EHD features are themselves sparse (meaning they contain a lot of ...
2
votes
1answer
45 views

Double pooling layers

In what scenario when assembling a DL CNN would you want to have two adjacent pooling layers, without a convolutional layer between?
0
votes
0answers
16 views

input shape of dataset in CNN [migrated]

My dataset is a simple table of 20 columns and 100,000 rows.It is not a image data as commonly used in CNN. What input shape should I provide in this case? Right now I did- ...
0
votes
0answers
44 views

Is there a software framework for simulating reduced precision (fixed point etc) training of neural networks

I mean a framework (could be an extension to Caffe or TensorFlow) which allows to see the effects of reduced numerical precision training when all computations like gradients, activations, weight ...
0
votes
0answers
5 views

Implementing spatio-temporal convolutions in pytorch [migrated]

I am trying to implement a layer to perform the (2+1)D convolutions described in this paper: https://arxiv.org/pdf/1711.11248.pdf The basic idea is as follows: Let's say I have a 3D convolutional ...
0
votes
0answers
12 views

What could be a baseline model in traditional approach for a Question and Answering System?

I am doing my research on factoid Question and Answering system. I am using the SQUAD dataset for my purpose. I could find many papers and journals on deep learning. But, I am also interested in ...
1
vote
0answers
51 views

Backpropagation of convolutional neural network - confusion [closed]

I've already seen many articles about this topic and Backpropagation In Convolutional Neural Networks by Jefkine (5 September 2016) seems to be the best. Although, as author said, For the purposes ...
2
votes
1answer
64 views

How good is good enough for fully autonomous vehicles?

To reach full autonomy in any fully automated device it must finish its task in such a way that human control is unnecessary. We know when the automation is excellent when there are no manual ...
3
votes
1answer
62 views

Identifying car model via deep learing

Is there any project or example for a software identifying cars? Situation: I got multiple angle shots in high resolution from a car. I want the algorithm to tell me "This is a Mercedes SLK" or "This ...
1
vote
0answers
18 views

In CNN (Convolutional Neural Network), does the combination of previous layer's filters make next layer's filters?

I know that the first layer uses a low-level filter to see the edge information. As the layer gets deeper, it will represent high-level (abstract) information. Is it because the combinations of ...
1
vote
0answers
32 views

How do GAN's generator actually work?

I have implemented DCGAN's myself and have been studying GAN's for over a month now. Now I am implementing the pggans but I encountered a sentence When we measure the distance between the ...
1
vote
0answers
24 views

deep learning, memorizing the input data not learning

I have 1000 data sentences in Turkish like "a esittir b arti c". The example sentence means "a = b + c". I basically want to translate mathematical Turkish sentences into math equations. For example, ...
5
votes
1answer
76 views

Why not teach to a NN not only what is true, but also what is not true?

I'm not a person who studies neural networks, or does anything that is related with that area, but I have seen a couple of seminars, videos (such as 3Blue1Brown's Series), and what I am always told is ...
2
votes
1answer
37 views

The use of classification algorithms nowdays

What is the utility today of traditional machine learning algorithms such as classification algorithms with the trend of deep learning? I mean can we still use the classification algorithms for some ...
2
votes
0answers
25 views

5 years later, are maxout networks dead, and why?

Maxout networks were a simple yet brilliant idea of Goodfellow et al. from 2013 to max feature maps to get a universal approximator of convex activations. The design was tailored for use in ...
3
votes
5answers
165 views

CNN with OpenCV

I have practiced building cnn for image classification with tensorflow, luckily to me they have very good library documentation and tutorials. But i found that tensorflow is too complicated, building ...
1
vote
1answer
39 views

What YOLO algorithm can I use for images with noise as I will implement it in real time

I want to detect drivers with, or without seatbelts at cross roads and for that, as it is real time, I am going to use yolo algorithm. For training data sets (the images) I need to collect, I placed a ...
2
votes
1answer
50 views

How to use Machine Learning with simple games?

I built a simple HTML game. In this game the goal is to click when the blue ball is above the red ball. If you hit, you get 1 point, if you miss, you lose 1 point. With each hit, the blue ball moves ...
1
vote
0answers
31 views

Deep learning model (LSTM) with temporal and non temporal attributes

I'm working on a project to predict the usage of all the files in a filesystem in near future based on the metadata of the file system for past 6 months. I've got the following attributes about the ...
1
vote
2answers
38 views

Convolutional neural nets and reduction of the layers

I have a very simple question about Conv nets. I understand the whole principle, but only one thing is not well explained on the Internet. If I have a 16 channels image that goes on a convolutional ...
3
votes
2answers
82 views

Wrong usage of 'Pose' in Matrix Capsules with EM?

In traditional computer vision and computer graphics, the pose matrix is a 4x4 matrix of the form ...
2
votes
2answers
72 views

What skills are needed to succeed at artificial intelligence field?

I am currently studying information systems engineering (BA) and I'm thinking of getting a master degree in Artificial Intelligence.So, What are the main important skills do I need to succeed at this ...
1
vote
1answer
41 views

What are the internal concepts incorporated in IBM's Watson platform?

IBM's Watson acts as a template for developing chat-bots with ease (without coding), but what are the methodologies and concepts that have been used to build it?
1
vote
2answers
47 views

How to build my own dataset and model for an LSTM neural network

I have a sort of mathematical problem and I'm not sure which model I should choose to make an LSTM neural network. Currently in my country, there is a system in which certain groups of researchers ...
4
votes
3answers
65 views

What kind of neural network architecture do I use to classify images into one hundred thousand classes?

I have an image dataset where objects may belong to one of the hundred thousand classes. I want to know what kind of neural network architecture should I use in order to achieve this.
2
votes
2answers
63 views

What is the purpose of “reshaping it into the shape the network expects and scaling it so that all values are in the [0, 1] interval.”?

I am a deep learning beginner recently reading this book "Deep learning with Python", the example explains the process of implementing a greyscale image classification using MNIST in keras, in the ...
1
vote
0answers
33 views

Data to Google Machine Learning

I have a database with hundreds of questions and answers. Would you like to know how I can work on this data in Google Cloud? I have a social network where I have these questions and answers, and I ...
1
vote
1answer
61 views

Thoughts on Apple Mac Pro vs GCP/AWS for Deep Learning?

I've been oogling the Mac Pro from Apple with loaded specs. Check it here if unfamiliar. I'm curious to hear anyone's thoughts of the computer for deep learning/machine learning applications vs ...
2
votes
2answers
68 views

Question classification according to chapters

I have a corpus, say an instruction manual. The text in this manual is grouped into chapters and each chapter is split up into sections. For example, Chapter 1/Section 1, Chapter 1/Section 2 and so on....
0
votes
0answers
16 views

Building a VAE architecture to reconstruct images

I am trying to build a VAE architecture in Lasagne which is able to reconstruct MNIST images. Note that I want to be able to sample from both the encoder and the decoder. So far, my architecture is ...
4
votes
2answers
96 views

What do neural connection weights represent 'conceptually'?

I understand how Neural Networks work and have studied its theory well. My question is at the intricacies of Deep Neural networks and perhaps is a bit beyond common understanding (as I have been told (...
6
votes
1answer
137 views

Is there any scientific/mathematical argument that prevents deep learning from ever producing strong AI?

I read Judea Pearl's The Book of Why, in which he mentions that deep learning is just a glorified curve fitting technology, and will not be able to produce human-like intelligence. From his book ...
2
votes
1answer
38 views

Action Probability with Thompson Sampling in Deep Reinforcement Learning

In some implementations of off-policy Q learning we need to know the action probabilities given by the behavior policy mu(a) (e.g., if we want to use importance ...
2
votes
1answer
110 views

Elon musk's comment on “non-benign AI scenarios”

I watched a youtube clip of Elon Musk talking about his view on the future of AI. He gave two examples. One of the examples was a benign scenario and the other example was a non benign scenario where ...
4
votes
1answer
56 views

Regression with more than one output, neural network

Currently in my country, there is a system in which certain groups of researchers upload information on products of scientific interest, such as research articles, books, patents, software, among ...
1
vote
2answers
100 views

Complete deep learning text classification with Python example

I would like to know if there is a complete text classification with deep learning example, from text file, csv, or other format, to classified output text file, csv, or other. I have seen tens of ...
0
votes
0answers
57 views

Speaker Diarization with LSTM paper

I am complete beginner in deep learning. I have a background in python. I would like to implement the following paper: https://arxiv.org/pdf/1710.10468.pdf. I do not understand the statistics behind ...
3
votes
1answer
69 views

Can some one help me understand this paragraph from Nvidia's progressive gan paper?

Furthermore, we observe that mode collapses traditionally plaguing GANs tend to happen very quickly, over the course of a dozen minibatches. Commonly they start when the discriminator overshoots, ...
2
votes
0answers
55 views

When can we say an RL algorithm learns an Attari game?

If a Attari game's rewards can be between -100 and 100, when can we say an agent learned to play this game? Should it get the reward very close to 100 for each instance of the game? or it is fine if ...