Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [deep-learning]

For questions related to deep learning, which refers to a subset of machine learning methods based on artificial neural networks (ANNs) with multiple hidden layers. The adjective deep thus refers to the number of layers of the ANNs. The expression deep learning was apparently introduced (although not in the context of machine learning or ANNs) in 1986 by Rina Dechter in the paper "Learning while searching in constraint-satisfaction-problems".

2027 questions
18
votes
4 answers

Issues with and alternatives to Deep Learning approaches?

Over the last 50 years, the rise/fall/rise in popularity of neural nets has acted as something of a 'barometer' for AI research. It's clear from the questions on this site that people are interested in applying Deep Learning (DL) to a wide variety…
NietzscheanAI
  • 7,256
  • 23
  • 37
10
votes
1 answer

A deep learning algorithm to optimize the outcome

I'm am quite new to deep learning but I think I found just the right real-world situation to start using it. The problem is that I have only used such algorithms to predict outcomes. For my new project, I need information to feed a machine with to…
Frank Malenfant
  • 131
  • 6
7
votes
1 answer

What is the most abstract concept learned by a deep neural network?

It seems that deep neural networks are making improvements largely because as we add nodes and connections, they are able to put together more and more abstract concepts. We know that, starting from pixels, they start to recognize high level objects…
alwaysLearningABC
  • 271
  • 1
  • 5
3
votes
1 answer

Non-Convex Loss Function in Deep Learning Is a Big Deal?

I want to use deep learning to estimate the value of a function based on some data. However, the loss function would be neither convex nor concave. Can I know if it is a big deal in deep learning? Is training a deep network, when loss function is…
Amin
  • 481
  • 2
  • 12
3
votes
1 answer

How to choosing the random value for parameter w in deep learning network?

I did watch the course DeepLearning of Andrew Ng and he told that we should create parameter w small like: parameters['W' + str(l)] = np.random.randn(layer_dims[l], layer_dims[l - 1]) ** 0.001 But in the last application assignment. They choose…
nguyen son
  • 33
  • 3
2
votes
0 answers

Setting learning rate as negative number for wrong train cases

I was watching a video which tells a bit about reinforcement learning, and I learnt that If the robot makes wrong movement then they train the network with negative learning rate. From this method, something came to my mind. My question is "Can I…
Faruk Nane
  • 73
  • 4
2
votes
0 answers

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, i have 6 sentence data. sentence ("a esittir b…
Faruk Nane
  • 73
  • 4
2
votes
0 answers

Possible to use codebase snapshots as input in deep learning?

I'm trying to predict grades within a course at my university. At the moment I manually extracting features, but I'm curious if it's possible to somehow use my entire dataset with a deep learning approach? I have data from throughout the course of…
Boye Borg
  • 21
  • 3
2
votes
1 answer

Applying NNs to 2d image noise reduction?

I'd like to explore possibilities of applying deep learning on image noise reduction problem, more on photographic camera noise. What's a good NN architecture to solve problems like this? EDIT 25,Nov,2017: I have a small dataset of clean/noisy…
Wangsta
  • 23
  • 3
2
votes
1 answer

How generate variation in datasets

I building a deep learning model to detect what drug user use. I have many symptoms and duration of each drug. I create X and y data but, for example, LSD have an effect duration of 180 - 720 minutes. I really need make 540 arrays? I really want a…
GIA
  • 568
  • 6
  • 22
2
votes
2 answers

Not able to find a good fit for a simple function with neural networks

I have been trying to adjust a neural network to a simple function: the mass of an sphere. I have tried with different architectures, for example, a single hidden layer and two hidden layers, always with 128 neurons each, and training them for 5000…
Hermes Morales
  • 221
  • 3
  • 11
2
votes
0 answers

Getting started with creating a general AI based on textual and then image based data?

I have a pool of knowledge that I want to mine for information and allow an AI to deduce likely conclusions from this information. My goal is to give the AI a set of textual data that is rated on a scale of 0 to 100 ranging from false (0) to…
ylluminate
  • 121
  • 1
2
votes
0 answers

Why are researchers focused on deep learning based stereo depth/disparity methods instead of non deep learning ones?

In recent years if you are working on stereo depth/disparity algorithms, it seems like you will only ever get your paper accepted to CVPR/ICCV/ECCV if there's some deep learning involved in it. A lot of authors published their code on github and…
user3667089
  • 121
  • 1
2
votes
0 answers

Current state of MoE models

I've been reading about Mixture of Expert models, and I've noticed that there is very little new work being produced in this subfield. Has there been a better method discovered? Why aren't more people doing stuff in this area?
Alex
  • 137
  • 5
2
votes
0 answers

Hinton's reading list from the removed Coursera MOOC

Geoffrey Hinton's Coursera MOOC was recently discontinued: https://twitter.com/geoffreyhinton/status/1085325734044991489?lang=en The videos however are still available at both on Youtube and on Hinton's…
Ahmet Umut Durmus
  • 21
  • 1
1
2 3