Complete Deep Learning In R With Keras & Others (Udemy.com)

The course contains valuable information about deep learning tools in R. It will significantly enrich my knowledge of the subject. The instructor's knowledge of the subject and her delivery is impressive.

The course contains useful and important information about the utility of various tools in R. The course is certainly going to enrich my knowledge base of the subject. the instructor is brilliant in explaining various aspects of the concept. Her knowledge of the subject is impressive.

This is an ideal course regarding the utility of different tools for deep learning in R. The course has immense potential for practical applications. The instructor has deep knowledge of the subject and her delivery is powerful.

The course contains vital and valuable information about the utility of important tools for deep learning in R. The concepts have vast opportunities for practical applications. I will be able to make use of this course to enhance the quality of my work. The instructor has thorough knowledge of the subject. Her lectures are precise and impressive.

This is a complete course containing important and useful information. the concepts of the course are very much relevant and useful for my work. The instructor has in-depth knowledge of the subject and explains the concepts in clear terms.

The course contains extensive information in a well-formatted manner regarding deep learning in R with Keras and others. The instructor has vast knowledge of the subject and effective communication skills. Overall very useful course and satisfying experience.

The problems were great in getting to actually practice the concepts. Speed was a good pace and the explanations were easy to understand. I loved the course. They gave a roadmap on how to proceed further and included a glimpse of more advanced concepts.

It is an excellent course to learn the basics of deep learning and using R with keras in real and theoretical work environments. Concepts are explained in an interesting way and easy to understand. A good course for building a solid foundation.

Not really, the tutor only explains the codes not what happens behind it. I can find these codes online. Moreover the codes are different and incomplete for some lectures. For example check section 4 ann classification with mxnet. the code uploaded is different than what is shown.

Thank you. The course is very informative and the instructor is extremely knowledgeable and moves at a very quick pace to provide explanations and examples about the workflow and concept of machine learning. It may be of value to check many of the coding examples and samples for code and data that do not seem to work well out of the box for "Complete Deep Learning in R with Keras and Others" . for example missing data, code, samples, CV files and packages and commands that often do not run due to packages not being installed, code not being provided, or errors being generated during the working samples. for example errors such as these " > library(keras) > > data = dataset_mnist() Error: Installation of TensorFlow not found. " > library(keras) > d2 = dataset_mnist() Error: Installation of TensorFlow not found. train = read_csv("digit-train.csv") Error: 'digit-train.csv' does not exist in current working directory > modelNnet = train(default~., + training, + method="nnet", + metric="ROC", + preProcess=c('center', 'scale'), + trace=FALSE, + tuneLength=1, + trControl=fitControl) > modelNnet Neural Network 22500 samples 23 predictor 2 classes: 'No', 'Yes' Pre-processing: centered (23), scaled (23) Resampling: Cross-Validated (10 fold) Summary of sample sizes: 20250, 20250, 20249, 20251, 20249, 20251, ... Resampling results: ROC Sens Spec 0.7210407 0.942078 0.38115 Tuning parameter 'size' was held constant at a value of 1 Tuning parameter 'decay' was held constant at a value of 0 > > summary(modelNnet) a 23-1-1 network with 26 weights options were - entropy fitting b->h1 i1->h1 i2->h1 i3->h1 i4->h1 i5->h1 i6->h1 i7->h1 i8->h1 i9->h1 3.63 0.43 0.14 0.08 0.11 -0.13 -2.74 0.24 -0.16 -0.37 i10->h1 i11->h1 i12->h1 i13->h1 i14->h1 i15->h1 i16->h1 i17->h1 i18->h1 i19->h1 -0.12 -0.23 0.25 -0.14 -0.47 -0.53 0.43 -0.18 1.14 2.76 i20->h1 i21->h1 i22->h1 i23->h1 0.63 0.14 0.98 0.09 b->o h1->o 0.97 -2.96 > > > predNnet= predict(modelNnet, testing) > cmNnet= confusionMatrix(predNnet, testing$default) Error: `data` and `reference` should be factors with the same levels. > cmNnet Error: object 'cmNnet' not found"