1
$\begingroup$

This question already has an answer here:

I am a first-year electrical engineering undergraduate student. I want to be an Artificial Intelligence scientist, and I want to make contributions to this field like Geoffrey Hinton. I think that AI will be a science soon and it includes neuroscience, computer science, and many other disciplines.

So I have started studied it, but I need to help with creating a road map. Currently, I am taking this class from Udemy https://www.udemy.com/machinelearning/. After finishing this course, I want to take Andrew NG's Coursera class, but I have no idea about what I will do after that. Do you have any suggestion? I want to study on SNN (Spiking Neural Network) and publish an article about this subject during undergraduate.

If you ask me why you take the Udemy course, I answer that I think that I should learn the code side of machine learning firstly, and second the course should give me mathematical intuition.

$\endgroup$

marked as duplicate by nbro, DukeZhou Jul 25 at 19:46

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

  • $\begingroup$ Hi Hueseyin and welcome to this community! A lot of other questions that are similar to yours have already been asked on this website in the past. So, I believe that this question is a duplicate of one or more of them. To see an exhaustive list of such questions, have a look at https://ai.meta.stackexchange.com/q/1532/2444. $\endgroup$ – nbro Jul 24 at 22:16
  • $\begingroup$ Apologies. I think this is a good question, but it's also a common question. Please review previous questions, and, if you feel you have a unique line of inquiry, feel free to edit and nominate for re-opening. (Closed provisionally) $\endgroup$ – DukeZhou Jul 25 at 19:45
  • $\begingroup$ I have a question,I have see plenty of course that is focused on career, and I think it does not include sufficient mathematical and theoretical stuff(for example in any course that I have seen,theory and proof of decision tree regression are not included) , so I think that I should learn from books, so Do you suggest any book that provides me to grasp theoretical ML.In other words,I want to read and understand articles on machine learning and AI $\endgroup$ – Huseyin Okan Demir Jul 25 at 19:48
  • $\begingroup$ @HuseyinOkanDemir To read and understand articles on machine learning, I suggest that you study very well linear algebra, calculus and multi-variable calculus, probability theory, statistics and numerical algorithms. I think it would be very good if you also have a very solid computer science background (so everything related to algorithms and data structures, programming, operating systems, etc). The math that is used in almost all ML articles requires only these mathematical prerequisites. Note that in the questions that I linked you to, there are some answers that suggest these too. $\endgroup$ – nbro Jul 26 at 20:46
-1
$\begingroup$

My recommendations beyond what you mentioned:

  1. Learn TensorFlow - there are many good courses on Udemy, Coursera and elsewhere.
  2. Coursera, Data Science Specialization - This is offered by Johns Hopkins University and will build a great data science foundation using R.
  3. Coursera, Deep Learning Specialization. This covers 5 courses: 1) Neural Networks and Deep Learning 2) Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization 3) Structuring Machine Learning Projects 4) Convolutional Neural Networks 5) Sequence Model
  4. Introduction to Natural Language Processing (NLP)
  5. Natural Language Processing with Deep Learning in Python

Once you learn all this material you will have a very good foundation.

There are lots of published papers and open source code that you should be able to find to learn about spiking neural networks. Here are just a few:

  • BindsNET - A Python package used for simulating spiking neural networks (SNNs) on CPUs or GPUs using PyTorch Tensor functionality.
  • Spiking-Neural-Network - This is the python implementation of hardware efficient spiking neural network. It includes the modified learning and prediction rules which could be realised on hardware and are enegry efficient. Aim is to develop a network which could be used for on-chip learning as well as prediction.

Article: Spiking Neural Networks, the Next Generation of Machine Learning

$\endgroup$
  • $\begingroup$ Thanks for answering. $\endgroup$ – Huseyin Okan Demir Jul 24 at 20:05
  • $\begingroup$ Watching a video course from an online university can't be called a foundation for the subject of Deeplearning. The information in the course are wrong, and it's up to the student to figure out why. The reason why students in a serious university have to write a thesis is because they have to explore knowledge from the past in a structured way. $\endgroup$ – Manuel Rodriguez Jul 25 at 9:37
  • $\begingroup$ I have a question,I have see plenty of course that is focused on career, and I think it does not include sufficient mathematical and theoretical stuff(for example in any course that I have seen,theory and proof of decision tree regression are not included) , so I think that I should learn from books, so Do you suggest any book that provides me to grasp theoretical ML. $\endgroup$ – Huseyin Okan Demir Jul 25 at 17:06
  • $\begingroup$ @ManuelRodriguez Let me remind you that Huseyin is a freshman in college. He is not going to work on a thesis for four or more years. He implied he was looking for online courses. The ones taught by Andrew Ng do review the mathematics involved in DNNs. Huseyin didn't ask us to advise him on college courses. I could have suggested some theoretical books but what good are they without a teacher when you are a freshman? The courses above will get him far ahead of his peers and when he is a junior or senior he will have a lot of knowledge to prepare him for more theoretical courses. $\endgroup$ – Brian O'Donnell Jul 26 at 0:00

Not the answer you're looking for? Browse other questions tagged or ask your own question.