I guess almost 70% of the class get A although I do not have exact statistics. There are 6 of them every 2 weeks. All classes at Ga. Tech should move to this platform and utilize it the way it was in AI 6601. Dont let these comments intimidate you. They may be old, but the quizzes will test your knowledge and there is mostly enough content to not need a thorough book reading. Have you ever enrolled in a course were the course content is great and they try to make it unnecessarily difficult? I averaged 20 hr/project and got to 100 on 5 of the 6 projects. I started the final exam on the Monday it was released and easily spent over 40 hours and took a day off from work to finish it on the following Saturday. Watch the clarification threads like a hawk. Decision trees (20 hours) - Relatively straightforward. Please also submit your submission.py to Canvas as backup. I went in knowing little about AI and came out knowing a bunch of algorithms but not to much on how to put it all together. You NEED to take this class seriously or else you will not get a B or A. The next three projects vary in difficulty quite a bit (we skipped #5 in the summer). Bad news is since this course trivially skims through topics, all youll come out with is some artificial intelligence and not real intelligence. The course is challenging and there is quite a bit of material covered, but most of it is interesting and I found the projects enjoyable. On the other hand, these are the only tests I have ever learned something on, maybe as much as the assignments. HOUSE 15 But no matter how many hours I spent on the assignments, I couldnt get everything to work correctly. At least that was the case for search, game playing, and variable elimination. In the end, I think the assignments are great and honestly, I kind of liked having to workout a bug in my code by solving the problem by hand because it definitely reinforced the concepts. I had a trip planned for the second half of the exam week, so I stayed up late the first half to power through it and submit it to get it out of the way. If you plan to take this course, bare in mind that it will require you to keep a rigorous schedule for studying, which must also be flexible enough to postpone other priorities to allow for more study time. I had my doubts, and I had an engineering degree, I work in data science field, and thought I could hack it. If you are new to Python but not programming in general and have experience in languages like C#, Java, C, etc. You will build a word recognizer for I come from a CS background and had 5 years working experience as a developer. With that being said, this course is still hard, and requires a serious time commitment. The exam was a trainwreck. If we use an admissible heuristic, we are guaranteed to find an optimal solution. Eugene Yan 2015 - 2022 So lots of good suggestions and helpful tips on Piazza. Unless youve got a 100 on five projects, dont think that you can skip one. 0.0125 rounds to 0.013 This was my favorite class in OMSCS (so far). Is that an ethical way to compensate for the unhelpful resources & TAs? While the exams were extremely challenging, I will admit that they do help you learn the material better. Some had restrictions on number of auto-grader attempts, but these specific assignments (markov models is one) were very easy. They are long and not easy. Because if it was, then those are just bare-faced lies. Assignment 6 wasnt difficult, but took more time than assignment 4 due to calculating the distributions by hand. Contrary to the popular opinion, I did not find this course difficult (final grade > 100%), much easier than RL and a little harder than AI4R. I found it much more challenging than the midterm and I believe this was due to the lack of relevance to the projects / lectures. I got an A without very much effort. The first two projects I found much harder than the rest, maybe 2x more effort to complete. Working on assignments was a big help to further digest what I learned. Lab #5 was a tough one. Give it another couple semesters to work out the bugs before taking this one. Why take a class if you know the assignments are super easy to implement. the transition probabilities of each state Consider that carefully. Modified local test case I kinda wish they had made each project smaller yet have more projects to cover all the topics we studied. The professor uses simple examples to explain AI concepts in the lecture videos, making this class friendly to people who do not have relevant CS/AI backgrounds like myself. The right graph is a different example, not the path from the video. 42, 40, 41, 43, 52, 55, 59, 60, 55, 47 However, since the teaching staff modifies the problem slightly each semester to mitigate plagiarism, the tests used to evaluate the implementations become broken. The algorithms get pretty complex, and I had quite a few nasty off by one bugs that required careful stepping to find. Having more time would allow for interesting programming assignments on topics such as neural nets, constraint satisfaction problems, etc. The B cutoff landed at roughly 78%. I got below the median on both Assignment 1(Search) and Assignment 2 (Game playing) even though I started on the Friday of the weekend that the assignment was due. So my advice is just not to worry so much about the score but rather, enjoy and focus on the knowledge you will gain from this great course. Not only are they challenging but they are also mentally taxing. This course is a very good course to go over AI in general. Indeed, the exams take quite a bit of time - budget for it. Although the concepts are really interesting. My only gripe with the course was the exams. Ill proceed by briefly listing pros and cons. That being said, some just breezed through. the projects are very interesting, but, unless you have experience in some related field, they will take a lot of your time. Positivity is good, but when it doesnt reflect reality, its not helping anyone. tl;dr : 6 VERY difficult projects, one every 2 weeks. Including extra credit, I finished with a >98% grade in the class. The assignments were both very straight forward and interesting. Overall this is a very interesting class. As a previous message said, if you have background in machine learning, you will already know a quarter of this course. The book is great for the first half of the semester, and ok for the second half. They are approachable with good preparation. what i learnt from this course is that maybe AI is not the area for me. Very hard, but very interesting. You will need to know and use a good amount of math as well. This content showed up later in the course for ALL students, which felt a bit unfair for the online students. This class has such potential. You are expected to know how to work with matrices and calculate basic probabilities. No complaints here really. who care? Every read of the text feels like I am working out my math muscles, and I usually end up getting tired of reading it or, on shorter chapters, feeling like I learned something. You think youre good reviewing the lectures and book? You would write it and it would seem to work with the crappy unit test you had. A Markov chain is a sequence of events with transitions based on certain probabilities. I expected this course to be pretty tough and time consuming based on previous reviews, but I never spent more than 15 hours a week on this class. 6: My assignments average was already high enough and since I was behind in the lectures I used the time for studying for the final. For example for the initial eval function testing board state, what should it return? There was no quality control, and the question quality varied drastically between the 10 sections. Exams were fair and open book. Word Frames My advice: If you want to take this course, definitely go for it! Piazza and slack discussions were helpful to break things down. This is another spot where I feel for students with less experience. In many of the other classes, (like Intro to CV or KBAI) the assignments, while hard, show polish from having been refined over the years rather than being rushed to meet production deadline. The level of effort required is just too great. Some of them are pretty complex. I have been a software engineer for years, so writing code and debugging is just another day to me. The grading seemed to cause some stress, since its based on the median and standard deviation, but rest assured that above a 90% is an A and above an 80% is at least a B. In addition, the office hours held by the TAs were immensely helpful for the assignments and lecturesI highly recommend attending them. I appreciated the bickering going on between reviews and edits so I wanted to chime in. So with this style, I was able to better understand some different uses for the concepts learned throughout the course. Youll have a much better time in this class if you just read/understand/follow the directions. starting as early as possible is the key. There is some good content in this class and I felt like I learned a decent amount about various areas of A. I., however the class in general feels unpolished in its current form and almost feels like a beta release. So, that is why it is difficult. Primarily being a survey of different AI techniques suited for various problem scenarios, this closely follows the book Artificial Intelligence: A Modern Approach by Stuart Russel and Peter Norvig. I did happen to find some errors in the textbook and wasted some time trying to understand stuff that didnt make sense. Final stats for Spring 18 were not released, but looks like B range was 72+ and A range was 87+. I probably spent 30 hrs/wk most most weeks, around 40 hrs for the week of the midterm, and honestly probably 50 hrs on the final. I usually did my homework and projects on the Sunday that they are due for other classes in the program and got an A on almost of all of them without much difficulty. when dealing with more complex sentences. I learned more from these exams than I have ever learned from an exam in the past. I loved this course and Id highly recommend it. Oh and I expect to get an A or a B depending on my final exam performance. What seems to set me apart from many others (based on my Piazza experience) is my ability to read and follow directions, and my understanding that sometimes I will need to do more than just watch the lectures to fully understand how to do the projects. The lectures are fun and easy to follow but you really learn a lot more from the assignments and reading the book. TLDR: very fun class, but come prepared and dont take it lightly. The class has multiple hundred students and the teaching staff releases grade distributions on each project, and in those distributions, there are very few people more than 1 standard deviation from the mean, and most of those are people who just didnt submit at all. You know how some games have a catch-up mechanic that helps people that are further behind help catch up to the rest? Some of them are must-knows for tech interviews. It is frustrating at times to implement everything from scratch but satisfying when you finally understood the concepts by working through them. Conceptually easier than A1 but however tests are more strict and is more difficult to get a full score. But, I did not like this course. A couple of the questions were poorly worded and caused many to lose points unnecessarily, but the TAs seemed to do their best to rectify that through either clarifications or by just giving points for certain questions. Instructor is very big on anti-plagiarism, just be aware. Definitely get the recommended book either buy it (you will not regret it as it is a great book) or get the online version. At minimum, I would recommend taking ML4T before this. I really should have dropped this course earlier. It was a great first class for someone who was still relatively new to core computer science concepts, but was fairly fluent in math and statistics. Like 5+ corrections per question on the exam, only noted on Piazza and not in the exam itself, some changing entire answers or answers, and some made on the final day the exam was due. What is the probability that the squad will have, A text file words.txt is given, which contains several words, one per each line. These projects weed a lot of people out of the class. colors represents time elapsed. Highly recommend. You can implement algorithms in Python/excel/etc. RWTH-BOSTON-104 Database). Also note that according to the honor code youre not supposed to refer to any content besides the lectures, the book, and what the TAs post. The unofficial slack was the saving grace for this course. Additionally, I completed a computer engineering undergraduate degree in 2014 as my only other exposure to computer science before this program. This is my second class (first was Computer Networks). probability, output that sequence with its probability. I found the assignments on decision trees and expectation maximisation to be somewhat easier, though HMMs were unfamiliar and required more time. The exams are extremely long. This is not a class where you can just skate by with limited coding skills. This is what I liked most about the course! And so you would have 8 lines of code where there was a bug but sometimes you just couldnt figure it out. Expectation-Maximization (EM) is the iterative algorithm which optimizes the parameters of the GMM. Overall, Ill recommend the class highly if you wish to explore & know more of what AI, ML etc is all about. A hard class with very interesting projects. If youre working, there might be a 50% chance you get 5 points of EC (2.5 pts expected value) but assignments are so hard there is like a 10% chance you only get 50 on an assignment (expected loss of 5 points). init Some extra credit on a few assignments allowed for strong homework scores to offset low exam scores if necessary. I think a few things could help students prior to taking the class: I felt like this class was definitely worth it for those interested in ML/AI and is probably better earlier in the program. A and B are independent events that both influence C. Here, C is the confounding cause, and in the absence of information about event C, A and B are still independent. Dont forget about Slack, too. This was an excellent class, but incredibly hard class. Piazza and slack were very helpful when it came to understanding how to do things. Again, I was lucky to still get an A since I have good assignment scores and extra credits and A covers more than half of the class, but still I think the cross-checking partial answers should serve the purpose of guarding vs minor mis-calculations, especially when the numerical questions have been clarified. omscs6601_assignment_6_ Assignment 6 for CS 6601_.pdf - 4/1/2020 But Piazza was also a source of noise and could be a little deflating. Almost every question requires the instructor to post a clarification on Piazza. The last 4 were relatively straightforward and didnt take too much time. First off, the easy projects arent easy. I did end up getting a good grade, but the class was a frustrating, disorganized mess and the TAs offered no support. Most of the time you spend will be on solving an assignment and researching. I was pretty burnt out. They are not hard. Start early if you can and dont hesitate to message the TAs. The content of the course is well designed to help you understand the fundamental concept of AI. We are given training data, which consists of the original word and its sequence. They cover lot of content in 3 months span . This course requires some pretty strong statistics , conditional probability theory , advanced math and python skills using vectorization with Numpy package. The first assignment was the most time consuming by a large amount. Some questions seemed to push the boundaries of what was taught in the class, while others were direct applications of stuff from lectures and previous exams. I found reading the book, then following it up with the lectures was helpful to confirm my understanding of the material as the lectures are much simpler. Its basically a series of quizzes that assumes you already know it. Overall nothing too bad but was annoying since youre already stressed out, The stress of your grade till the very end of the class. Lectures: Its true that the first two assignments are harder, but I wouldnt say that the rest of the assignments are a walk in the park. Projects are coding based, in python. For more information on GMMs and EM, refer to this excellent video! Prepare enough time, since one weekend is probably not enough. Hopefully those videos are updated at some point. This is a survey course in AI and a great one! 5 hrs giving a walk through of midterm; something that we dont see too often by any Prof of that class & calibre (such things are generally dealt by the TAs). The exams. While the questions were not particularly difficult, it ended up being extremely time consuming and stressful since I had to sort through many possible interpretations of each question to try to figure out what was being asked. So its very useful for anyone who wants to work on AI/ML in the future. I just wish that the learning came more from the modules themselves than external research, and that we were tested on the actual concepts learned from the coursework rather than what felt like a pool of AI topics. The final.man. At the time of this writing (Fall 2018), one of those courses would involve completing the six assignments that are each 2-3 weeks long, of which only five count towards your grade. Solid course. I solved this practice exam and felt that it was a lot of work, but the right amount for a week-long open-book exam. The first two assignments were pretty time consuming but well worth it, and it got easier from there. Both Midterm and Final are a 30-50 pages PDF with open questions/exercises to do at home in a week. It was not as hard as before. Personally, I dont really think you learn too much when pseudocode is provided because nearly everyone who can program can implement it. Gradescope was nice because it was instantaneous and left no doubt where you stand gradewise. This class seems like it would be very difficult for someone new to programming. As stated above, I have never touched probability or statistics so I came in completely new to the subject and concepts of Bayes Theorem and Bayes Networks. The best five contributed a total of 60% to the total grade. The next four assignments required more math and stats and less coding, but conceptually very challenging. Thads lectures are pretty good for the most part. I am not a big fan of AI and all the hype surrounding it, but still enjoyed half of the material and was a good exposure to it, so although it was hard, I am glad I took it. Now I have confidence I can survive anything. This course includes several AI topics. I went from A/B boderline to B/C borderline in one assignment. One thing that impressed me the most was Thad spending 2. The algorithms given in book are in most cases better explained elsewhere, for example in the authors own videos. Apparently the curve is generous, so supposedly everybody will be getting Bs or As. The material was super interesting. Like I said in my advice, if youre interested in the topic and you feel you have the prerequisites covered, absolutely go for it! The videos were from three different people and had dramatically different quality. Pros: I preferred the lectures taught by the professor (vs the ones taught by the guest lecturers). 2 lost your interest in AI. It isnt impossible, but it isnt easy. My only complaint would be the Norvig lectures, theyre pretty dry/bad. The XYZ_test. Subject itself is good. Everyones background and strengths differ, so whats challenging to one person may not correlate with another. The midterm was still a learning experience and I think i walked away with a lot more knowledge in that class. There was always something that I should be working on throughout the semester and that was exhausting at times, to the point that I regrettably skipped the final assignment to catch up on learning materials to prepare for the final. I struggled the most with the third lab and this is where I understood why this class is considered hard. Although if you find the field interesting you will find it hard not to put in more time and will not regret it. Set aside time for exams if youre working so you can check your work. If you are looking to buy and keep the book: get the 4th. Its got a ton of information and some of the algorithms are broken down well. This made midterms and finals a lot harder and time-consuming than they should be. I can tell every assignment was challenging and required a significant amount of effort to complete. If you actually have the prerequisites outlined, youll spend much less time on it than I have and probably enjoy it. books was good (as much as i could keep up with reading it) but also there were a lot of resources online to help, TAs were great help during office hours and on piazza, love coding in python and this was all in python.