Just a recap, in my previous post, I had primarily looked upon amount, structure of data that needs to be served as input to machine learning and the process used for its implementation. In this post, we are going to continue to learn more about the tools/techniques and hardware that will be required for these processes to excel.
While the majority of us are appreciating the early applications of machine learning, it continues to evolve at quite a promising pace, introducing us to more advanced algorithms like Deep Learning. Why DL is so good? It is simply great in terms of accuracy when trained with a huge amount of data. Also, it plays a significant role to fill the gap when a scenario is challenging for the human brain. So, quite logical this contributed to a whole slew of new frameworks appearing. Please see below the top 10 frameworks that are available and their intended use in the relevant industry space.
Just to provide a comprehensive analysis of the best tools that would undoubtedly recommend. So what is the final advice?
The speed of your algorithm is dependent on the size and complexity of your data, the algorithm itself, and your available hardware. In this section, we’re going to focus on hardware considerations when:
- Training the model
- Running the model in production
Some things to remember:
If you need results quickly, try machine learning algorithms first. They are generally quicker to train and require less computational power. The main factor in training time will be the number of variables and observations in the training data.
Deep learning models will take time to train. Pre-trained networks and public datasets have shortened the time to train deep learning models through transfer learning, but it is easy to underestimate the real-world practicalities of incorporating your training data into these networks. These algorithms can take anywhere from a minute to a few weeks to train depending on your hardware and computing power.
Training the Model
Desktop CPUs: are sufficient for training most machine learning models but may prove slow for deep learning models.
CPU Clusters: Big data frameworks such as Apache Spark™ spread the computation across a cluster of CPUs.
The cluster or cloud option has gained popularity due to the high costs associated with obtaining the GPUs, since this option lets the hardware be shared by several researchers. Because deep learning models take a long time to train (often on the order of hours or days), it is common to have several models training in parallel, with the hope that one (or some) of them will provide improved results.
GPUs: are the norm for training most deep learning models because they offer dramatic speed improvements over training on a CPU. To reduce training time it is common for practitioners to have multiple deep learning models training simultaneously (which requires additional hardware).
Running the Model in Production
The trend toward smarter and more connected sensors is moving more processing and analytics closer to the sensors. This shrinks the amount of data that is transferred over the network, which reduces the cost of transmission and can reduce the power consumption of wireless devices.
Several factors will drive the architecture of the production system:
- Will a network connection always be available?
- How often will the model need to be updated?
- Do you have specialized hardware to run deep learning models?
Will a network connection always be available?
Machine learning and deep learning models that run on hardware at the edge will provide quick results and will not require a network connection.
How often will the model need to be updated?
Powerful hardware will need to be available at the edge to run the machine learning model, and it will be more difficult to push out updates to the model than if the model resided on a centralized server.
Tools are available that can convert machine learning models, which are typically developed in high-level interpreted languages, into standalone C/C++ code, which can be run on low-power embedded devices.
Do you have specialized hardware to run deep learning models?
For deep learning models, specialized hardware is typically required due to the higher memory and compute requirements.
We have now looked through the different frameworks/tools and techniques that are prevalent in the industry for Machine and Deep Learning initiatives in your organization. We also looked through the recommendation on which framework works for your specific request. Also we looked at the Hardware that is required to run these models Or to make the frameworks active.
Stay tuned…. Part 4 of this foray, we will look into Usage of all these Machine and deep learning algorithms, models and frameworks that are prevalent in the industry.
Please feel free to review my earlier series of posts on AI-ML Past, Present and Future – distributed across 8 blogs.
Authored by Venugopala Krishna Kotipalli