I've been working on the Beam Search algorithm for a scheduling problem
I have a question about it, is a a Deep Learning tool (as it uses RNN) or an AI heuristic ?
Thank you
I still cannot understand fully the difference between AI and Deep learning
Related
I know there are quite many hands-on tutorials about deploying BERT or other models. But the problem is many of them are just shallow user cases which only modified a few parameters using apis from a certain libraries such as keras. I am a novice and I often find my still confused at the details and variational steps when deploying pre-trained language models on my projects.
Could anyone give a hint on what is a better roadmap for learning coding with pre-trained language models, including any resources, articles, or tutorials, etc.
I have read many articles on Medium. But most articles there seems only introduc the general concepts, rather than providing the real know-how when learning it.
I find these two courses very novice-friendly:
Hugging Face course
https://huggingface.co/course/chapter1/1
Deep Lizard "Deep Learning Fundamentals - Classic Edition"
https://deeplizard.com/learn/playlist/PLZbbT5o_s2xq7LwI2y8_QtvuXZedL6tQU
hi im super new to this field(deep learning, computer vision)
so this question may sound dumb.
In this link (https://github.com/GeorgeSeif/Semantic-Segmentation-Suite), there are pre-trained models (eg, ResNet101) called front end models. And they are used for Feature Extractor. I found these models are called backbone models/architectures generally. And the link says some of main models(eg. DeepLabV3, PSPNet) rely on pre-trained ResNet.
Also, Transfer Learning is to take a model trained on a large dataset and transfer its knowledge to a smaller dataset, right ?
Then my question is ,
1.Do the models that rely on pre-trained ResNet do transfer learning basically ?
2.if i use pretrained network like ResNet101 as backbone architecture of main model(like U-Net,SegNet) for image segmentation, is it considered as transfer learning ?
Sorry for my bad english,and i would highly appreiate if you answer this questin. Thank you.
I'm studying Image Recognition with Tensorflow. I already read about the topic How to retrain Inception's Layer for new categories on Tensorflow.org, which utilize the Inception v3 training model.
Now, I desire to creat my own CNN model in order to compare with Inception v3, but I don't know how can I begin with.
Anyone knows some guides step-by-step on this problem?
I'd appreciate any your suggestion
Thanks in advance
First baby steps
The gold standard for getting started in image recognition is processing MNIST images. Tensorflow has a great tutorial on how to get started and also how to move to convolutional networks.
From there it is a long hard road to compete with Inception without just copying someone else's graph. You'll probably want to get a feel for what the different layers of convolution do. I created a basic Tensorflow Tutorial which contains an example python file that demos different convolution graphs and their resulting accuracy.
Going deeper
After conquering MNIST you'll need a lot of images (you can get them from imageNet) and a lot of GPU (to run all your training) and a software setup so that you can not only run and test your model, but dozens (if not hundreds) of variations to explore your hyper parameters (like learning rate, convolution size, dropout, etc). Remember, it took a team of leading edge Machine Learning experts to create something like Inception, many many months (possibly years) of iteration to find the model they use today, and thousands of CPU/GPU hours.
If you are trying to understand what is going on and what makes a good graph, then trying to recreate Inception is a great idea. If you just want an excellent Image recognition model, then reuse an existing one.
If you are trying to have fun, just do it!
Cheers-
I'm using joint positions from a Kinect camera as my state space but I think it's going to be too large (25 joints x 30 per second) to just feed into SARSA or Qlearning.
Right now I'm using the Kinect Gesture Builder program which uses Supervised Learning to associate user movement to specific gestures. But that requires supervised training which I'd like to move away from. I figure the algorithm might pick up certain associations between joints that I would when I classify the data myself (hands up, step left, step right, for example).
I think feeding that data into a deep neural network and then pass that into a reinforcement learning algorithm might give me a better result.
There was a paper on this recently. https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf
I know Accord.net has both deep neural networks and RL but has anyone combined them together? Any insights?
If I understand correctly from your question + comment, what you want is to have an agent that performs discrete actions using a visual input (raw pixels from a camera). This looks exactly like what DeepMind guys recently did, extending the paper you mentioned. Have a look at this. It is the newer (and better) version of playing Atari games. They also provide an official implementation, which you can download here.
There is even an implementation in Neon which works pretty well.
Finally, if you want to use continuous actions, you might be interested in this very recent paper.
To recap: yes, somebody combined DNN + RL, it works and if you want to use raw camera data to train an agent with RL, this is definitely one way to go :)
Has anybody seen a GP implemented with online learning rather than the standard offline learning? I've done some stuff with genetic programs and I simply can't figure out what would be a good way to make the learning process online.
Please let me know if you have any ideas, seen any implementations, or have any references that I can look at.
Per the Wikipedia link, online learning "learns one instance at a time." The online/offline labels usually refer to how training data is feed to a supervised regression or classification algorithm. Since genetic programming is a heuristic search that uses an evaluation function to evaluate the fitness of its solutions, and not a training set with labels, those terms don't really apply.
If what you're asking is if the output of the GP algorithm (i.e. the best phenotype), can be used while it's still "searching" for better solutions, I see no reason why not, assuming it makes sense for your domain/application. Once the fitness of your GA/GP's population reaches a certain threshold, you can apply that solution to your application, and continue to run the GP, switching to a new solution when a better one becomes available.
One approach along this line is an algorithm called rtNEAT, which attempts to use a genetic algorithm to generate and update a neural network in real time.
I found a few examples by doing a Google scholar search for online Genetic Programming.
An On-Line Method to Evolve Behavior and to Control a Miniature Robot in Real Time with Genetic Programming
It actually looks like they found a way to make GP modify the machine code of the robot's control system during actual activities - pretty cool!
Those same authors went on to produce more related work, such as this improvement:
Evolution of a world model for a miniature robot using genetic programming
Hopefully their work will be enough to get you started - I don't have enough experience with genetic programming to be able to give you any specific advice.
It actually looks like they found a way to make GP modify the machine code of the robot's control system during actual activities - pretty cool!
Yes, the department at Uni Dortmund was heavily into linear GP :-)
Direct execution of GP programs vs. interpreted code has some advantages, though in these days you'd probably rather want to go with dynamic languages such as Java, C# or Obj-C that allow you to write classes/methods at runtime while still you can still benefit from some runtime rather than run on the raw CPU.
The online-learning approach doesn't seem like anything absolutely novel or different from 'classic GP' to me.
From my understanding it's just a case of extending the set of training/fitness/test cases during runtime?
Cheers,
Jay