Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

Deep learning defied?

t_emmert
Beginner
1,142 Views

 I am new to the theories and application of inference engines and ML. 

1.) Does the dynamic flow of tensor directions create an "adaptive deciion table?"

and

2.) What is the defining difference between complex machine learning and an inference engine from a developer's point of view?

 

0 Kudos
1 Solution
Megat_Intel
Moderator
1,119 Views

Hi T_emmert,

Thank you for reaching out to us.

 

Are you asking about the OpenVINO™ toolkit? Regarding the dynamic flow of the tensor, I will check with the relevant team on this.

 

On the other hand, Machine Learning focuses on data and algorithms to make decisions/predictions. Machine Learning uses algorithms to understand the data, learn from it, and then make a decision/prediction.

 

Deep Learning is a subset of Machine Learning and will structure algorithms with three or more layers to create a neural network. The neural network learns from large amounts of data and makes decisions and predictions. The hidden layer of the neural network also helps to optimize and refine the accuracy.

 

For your information, OpenVINO™ toolkit enables you to optimize deep learning models from many frameworks and deploy them with performance on a range of Intel® processors and other hardware platforms. OpenVINO™ Runtime/Inference Engine is a software component that contains complete implementation for running the AI inference on Intel hardware devices (e.g.: CPU, GPU, VPU, etc.). The inference engine plugin implements the unified API and provides additional hardware-specific APIs.

 

 

Regards,

Megat


View solution in original post

0 Kudos
4 Replies
Megat_Intel
Moderator
1,120 Views

Hi T_emmert,

Thank you for reaching out to us.

 

Are you asking about the OpenVINO™ toolkit? Regarding the dynamic flow of the tensor, I will check with the relevant team on this.

 

On the other hand, Machine Learning focuses on data and algorithms to make decisions/predictions. Machine Learning uses algorithms to understand the data, learn from it, and then make a decision/prediction.

 

Deep Learning is a subset of Machine Learning and will structure algorithms with three or more layers to create a neural network. The neural network learns from large amounts of data and makes decisions and predictions. The hidden layer of the neural network also helps to optimize and refine the accuracy.

 

For your information, OpenVINO™ toolkit enables you to optimize deep learning models from many frameworks and deploy them with performance on a range of Intel® processors and other hardware platforms. OpenVINO™ Runtime/Inference Engine is a software component that contains complete implementation for running the AI inference on Intel hardware devices (e.g.: CPU, GPU, VPU, etc.). The inference engine plugin implements the unified API and provides additional hardware-specific APIs.

 

 

Regards,

Megat


0 Kudos
Megat_Intel
Moderator
1,087 Views

Hi T_emmert,

For your information, OpenVINO™ toolkit does not have dynamic flow of tensors, and the adaptive decision table is also not OpenVINO™ related.

 

On the other hand, you can check out this study on Dynamic control flow in large-scale machine learning (This is an external link and is not maintained by Intel) that explained on programming model for distributed machine learning that supports dynamic control flow. Hope this helps.

 

 

Regards,

Megat


0 Kudos
t_emmert
Beginner
1,036 Views

Megat_intel,

 Thank you for your response and the links. I apologize for my earlier misspellings. 

Regards,

Troy

0 Kudos
Megat_Intel
Moderator
1,027 Views

Hi Troy,

This thread will no longer be monitored since we have provided suggestions. If you need any additional information from Intel, please submit a new question.

 


Regards,

Megat


0 Kudos
Reply