We changed our privacy policy. Read more.
33

Keras is a simple and high-level neural networks library, written in Python, that works as a wrapper for Tensorflow and Theano. It's easy to learn and use. Using Keras is like working with Lego blocks. It was built so that people can do quick experiments and proofs-of-concept before launching into a full-scale build process. With that in mind, it was made ...


5

Interpreted languages allow for a faster development cycle, as they don't require time for compilation, and fragments can often be run without having a complete program. They often also have fewer constraints for variable declaration or typing. That means they can be used to quickly scope out a problem and try different solutions. The drawback is the slower ...


4

I don’t know for certain, but I can make a guess. This is just my opinion, some others may disagree. The field of ALife has four branches that I’m aware of: Self-Organizing/self assembly behavior. This is the application you refer to, another context it’s useful is swarm control (for drone swarms, for example). While this is technically ALife, as far as I’m ...


4

While dyedgreen is right in some respects, I don't agree entirely with that sentiment. Sure, you can theoretically use any language as long as you know the maths and understand the concepts inside and out whilst having some applicable knowledge. However, I don't believe if you are starting from scratch, you should learn to develop models in Java. While the ...


3

TensorFlow was developed by Google and is based on Theano (Python library), while Facebook developed PyTorch using the Torch library. Both frames are useful and have a great community behind them. Both provide machine learning libraries to accomplish various tasks and do the job. TensorFlow is a powerful and deep learning tool with active visualization and ...


3

Of course, whether or not you will need to know and use C++ depends on the topics you will research during your Ph.D. or job. If you'll need just to use and/or combine some existing ML models (yes, in a Ph.D., you're expected to come up with new ideas/tools), then you won't probably need to know C++, as the most commonly used libraries for machine learning ...


3

If you want to do machine learning without coding (eg visual programming) you can try : Orange : https://orange.biolab.si/ . It also come when you download the Anaconda distribution. Also there is Dataiku Data Science Studio (the free version). https://www.dataiku.com/dss/trynow/ But in general I would not recommend doing machine learning / data science ...


3

In recent times different data science magazines and institutions have published their reviews of the top AI toolkits. In these reviews they tend to highlight the innovative features possessed by each platform as well as their reliability and ability to scale. Below are a some evaluations of AI platforms that I recommend you have a look at: KDnuggets ...


2

Visual methods are limited and you will soon find the time invested in coding may have been better. There are various softwares like Weka [website] or Rapid Miner (Not free) [website] or Orange [website]. Nice thing is they provide GUI as well as coding. So you can import Python or R script in rapid miner for example. But I would recommend that you should ...


2

I don't think there is much merit in using one language over the other. It's true that you will get a better feeling for what libraries etc. are available in Python when using it, but I think it's more important to focus on the mathematics and application of the algorithms and techniques you will learn, as these will be relevant regardless of the language / ...


2

Since you are A C# developer already Just getting started and not sure where to go next I would suggest trying the Emotion API which is now part of the general Face API. This has the benefit of being pre-trained on a very large dataset. You can perform 30,000 recognitions/month for free.


2

The Intel Movidius Stick is an USB stick for running a neural networks (that are programmed in Tensor Flow) on resource scare devices such as a Raspberry Pi (in order to reduce the traffic by sending data to cloud service or a server with more capacity where your neural network runs). Tensor Flow is a programming framework which can be used as python ...


2

In recent years the focus has been on layers rather than the more biologically inspired individual nodes. As stated in the comment by thecomplexitytheorist you could use a computational graph, although then you have issues with distribution and you're limited to one framework. I created something in my PhD about the same time as the thesis you reference ...


2

You might want to look into building convolutional neural network (CNN) for object detection using Keras. With plain white squares, it should work pretty good.


2

As @Clement mentions, text_gen_description gives a good overview!, but the paper seqGAN paper describes the REINFORCE approach more in depth, as they are the first to do it (i believe). This is probably the approach most take now of days when going the GAN route. Note that just basic MLE training has shown promise with openAI's GPT2. When i need a text ...


2

TLDR Use whatever environment you are most comfortable with. Today the choice of operating system is of much less importance than few years ago. Generally speaking, you will have more application choices under Linux, however, some of these choices will be less than spectacular :-) Windows works better with some hardware. Hence, under Linux, it is a very ...


2

I'm going to go ahead and disagree with the others. From an academic perspective for AI or any CS related assignment Java (or C or C++) will always have much more benefit as you will get to write the actual code instead of using libraries others have already written. That way later on when you transition to Python or whatever language you choose you'll ...


2

You could try Mesa. It has various examples that are commonly-used in agent-based modelling, like Epstein's model, a wolf/sheep predator/prey model, and many more. There is also an introductory tutorial.


2

In my experience, knowledge of any particular programming language does not matter. What matters is that you can quickly pick up the basics of a given language. In my professional work I have been programming in Scala, Java, Groovy, and now Lisp; I didn't really know any of these languages before my working with them (except for Java). But I have been able ...


2

Q-values represent expected return after taking action $a$ in state $s$, so they do tell you how good it is to take an action in the specific state. Better actions will have larger Q-values. Q-values can be used to compares actions but they are not very meaningful in representing performance of the agent since you have nothing to compare them with. You don't ...


1

No, it appears to take large amounts of screenshots to generate the images to be used for training. Don't waste your money. I would say you could try training on Google's colab if you can upload the training data.


1

The evaluation of the last steps in the game can be made with the 1 and 0 as you said. For all the other steps, the evaluation should be the evaluation of the best next step with a small decay.


1

This is supposed to be a comment but I haven't got enough reputation to do that. In addition to what @the complexitytheorist has said, I recommend you to have a deeper look at your data first, using dimension reduction and visualisation methods such as PCA and t-SNE. A better understanding of data may always save you a lot of work. Then you can choose ...


1

I would recommend to have a look at Finding Groups in Data, which is a very readable introduction to clustering methods. It gives a good overview over a number of different algorithms, both agglomerative and hierarchical. As far as I remember, source code for the various algorithms is available on the web somewhere. I am sure you will find a fitting ...


1

I can't do a better job at explaining than Jeremy Howard's team did. Follow carefully and systematically all the steps put together here. You can read more about the different types of machines here, about the possible choices of GPUs here and about the regions and zones here. Follow the fastai course too. I can't emphasize how good is it. You can find ...


1

Human evaluation is the gold standard as stated in this podcast by Asli Celikyilmaz, even if you only test a very small part of the generated text. You needed an automated method and this one: BLEURT by Google would be helpful. It's a flexible, semantic-level metric/model trained in a multi-stage way: 1) masked language model like BERT; 2) pre-training on ...


1

This is a tricky issue. I assume you are using transition probabilities to pick the next suitable word, so you could use some other corpus data, derive probabilities from it, and compare those to your system. Not very satisfactory, though, as you might end up evaluating the system in a circular way, deriving your test data in the same way as you generate ...


1

Knime is my favorite - it is the Gartner Leader Quadrant - available for free. Also consider Rattle (for R) and Gretl for econometrics/stats. These are good tools for the Citizen Data Scientist.


Only top voted, non community-wiki answers of a minimum length are eligible