Week 4 - BALT 4364 - CH 4

-

 Chapter four covers a topic that I think is hard for most people to understand, including myself. That topic would be deep learning, and I get caught up in trying to figure out how something that is not "alive" is able to learn. Lucky for me, this chapter was able to answer some of those questions. The computers use neural networks similar to the structure and functions of the human brain. What separates deep learning from other types of machine learning is the fact that it can learn from the data on its own without us telling it what to look for. In my opinion, that is amazing and scary at the same time.

So, what are some examples of deep learning that we interact with? Our phones have a couple of good examples. Siri uses speech recognition deep learning, while face recognition also implements this technology. The end of the chapter provides us with some ChatGPT prompts that I thought would help me make sense of some of this, but I decided to add a prompt of my own. I asked ChatGPT if deep learning is expensive to implement, and this is what it responded with:

Why it can be expensive

  • Hardware costs: Training deep learning models often requires GPUs or specialized chips, which can be costly to buy or rent.

  • Large datasets: Deep learning typically needs a lot of data, which can be expensive to collect, label, and store.

  • Energy usage: Training large models uses a lot of electricity.

  • Specialized expertise: Hiring data scientists or engineers with deep learning skills can be costly.

Why it’s not always expensive

  • Pretrained models: You can use models that are already trained (like image classifiers or language models), which drastically reduces cost.

  • Cloud services: Providers like Google, AWS, and Microsoft rent GPU time so you don’t need to buy hardware.

  • Smaller models: Many modern deep learning models are efficient and inexpensive to run.

  • Open-source tools: Frameworks like TensorFlow and PyTorch are free. 

My interpretation of this is that it is not a lot of companies would benefit from training their own deep learning models. But the potential benefits are worth the risk for companies that have the resources. 


Comments

Post a Comment

Popular posts from this blog

Jude's Introduction Post 4361-4364

-
Image
Welcome to my blog!  My name is Jude Sullivan, and this will be my third Fall here at Benedictine. I am originally from Paris, Illinois but made the decision to move across the country and continue my baseball career in warmer weather, at the Mesa campus. I played on the baseball team my first two years, but I have decided to focus on school/work for this Fall semester. I will be graduating in December with an Accounting degree, and I am looking forward to learning the skills that this class will require.
Read more

Week 8 - BALT 4362 - AI Image and Video Generation

-
Image
AI’s ability to create realistic images and artwork has exploded in the last few years, and in my opinion, it is both amazing and terrifying. With the correct prompt, anyone can make professional-quality pictures, no art degree required. Businesses can now use tools like DALL·E, Midjourney, and Canva’s AI generator to design posters and logos in seconds. This levels the playing field for small businesses that do not have the marketing budget to compete with bigger corporations. This can also be applied to students. You can make visuals for class projects, creative writing, or social media without needing advanced design skills. I know I have been able to use it to create presentation visuals I never would have been able to come up with on my own. It does a great job bridging the gap for people who might lack creativity, like me.  But as cool as it is, there are some real downsides. Artists worry about AI copying their work or taking credit for their style, and some AI-generated im...
Read more

Week 2 - BALT 4363 - CH 2

-
Image
Chapter Two of Data Toolkit,  and more specifically the exercises within the chapter,   helped me understand the basics of how Python can control and organize what a program does. Control structures like loops are like giving a set of instructions that the computer can follow repeatedly or only under certain conditions. The examples using “for” and “while” loops made it clearer how repetition works. An example of this would be repeating something a certain number of times or until a condition changes. I liked the comparison to a remote-control car, because it helped me see how code can “steer” what happens in a program. Seeing the examples with “if” and “if-else” statements helped me see how Python can make decisions, like checking whether a number is even or odd. The guessing game example at the end was especially interesting because it combined all the ideas, loops, conditions, and user input into one project. It made Python feel a little less intimidating, since I could se...
Read more