Erika Andersen on Be Bad First, Part 10

In the book, Be Bad First: Get Good at Things Fast to Stay Ready for the Future, Erika Andersen shares her mindset and techniques for learning new things well and quickly.

These are some of my favorite concepts and takeaways from reading the book.

Chapter 8: Slaying Your Personal Dragons: One the Road to Mastery

In this chapter, Erika Andersen discusses some of the personal challenges we will face when we try to become high-payoff, Michelangelo-style learners. She offers the following observations and recommendations for us to think about:

For questions on Endless Curiosity:

Q: But some things are just BORING. How can I possibly get curious about stuff that makes me want to go to sleep?

A: Nothing is intrinsically dull – it has more to do with the lack of interest on our part. It is, however, possible to get interested in anything. That is a much more productive belief than the other way around. Holding the idea that some things are, by their very nature, uninteresting will limit us from a lot of learning.

Q: Can you be too curious?

A: If we define curiosity as “a deep need to understand and master,” we cannot be too curious. We also need to be mindful of some things that masquerade as curiosity and lead us to produce bad results. One such fake curiosity is our need to control everything and micromanage our environment. Micromanaging, even if it’s disguised as curiosity, is “thinking we already understand something and that we need to make other people better at doing it.”

Another kind of fake curiosity is “endless divergent thinking.” Endless divergent thinking can lead us to brainstorm and fact-finding missions, but we never settle on a course of action. It wastes mental and emotional energy that could be better used for authentic learning.

Q: I’m worried I’ll look dumb if I ask questions that demonstrate my lack of knowledge or understanding. What if I’m the only one who doesn’t know?

A: When we ask curious questions, it is not that we look dumb but think we will look dumb. One way to shift our self-talk in this area is to think of someone we respect who is willing to ask “novice” questions. We should ask ourselves, Do I think that person looks dumb when he asks an I-don’t-know type question? One caution is to avoid the novice trap of asking a curious question already covered in the conversation because we failed to pay attention.

Q: When people talk about things I don’t know about, I lose focus fast. How can I stay engaged?

A: When someone is discussing a new topic, our minds can take one of two directions. One direction is curiosity, and the other direction is disinterest. If we are losing focus, we are walking down the path of disinterested self-talk.

One technique to reengage our curiosity is summarizing what the other person is saying. To digest something someone is saying, we first have to understand it. If we try to understand what someone is saying well enough to summarize it, we begin listening as though we are curious.

The essence of curiosity is the need to understand. Once we pay attention to something this trying-to-understand way, our actual interest often gets catalyzed, and we find ourselves engaged in the topic.

接受與否認

(從我一個尊敬的作家,賽斯·高汀

讓事情變得更好的最好方法是先看看它們目前的情況是怎樣的。然後看能做點什麼。

承認問題並不等於是放棄。

很多時候,我們寧願不想聽到它,或者我們選擇災難化來保護自己,去避免接受實際發生的事情的影響。

否認主義並不是個長期的戰略。

Binary-Class Image Classification Model for Pistachio Identification Using TensorFlow Take 5

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: The project aims to construct a predictive model using various machine learning algorithms and document the end-to-end steps using a template. The Pistachio Identification dataset is a binary-class modeling situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: Pistachio nut has an important place in the agricultural economy; the efficiency of post-harvest industrial processes is crucial to maintaining its economic value. The industry needs new methods and technologies for separating and classifying pistachios to provide this efficiency. In this study, the research team aimed to develop a classification model different from traditional separation methods based on image processing and artificial intelligence techniques.

A computer vision system (CVS) has been developed to distinguish two species of pistachios with different characteristics that address additional market types. The research team took 2148 sample images for these two kinds of pistachios with a high-resolution camera. They applied image processing, segmentation, and feature extraction techniques to the images of the pistachio samples.

ANALYSIS: The InceptionV3 model’s performance achieved an accuracy score of 99.19% after 5 epochs using a separate validation dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 98.37%.

CONCLUSION: In this iteration, the TensorFlow InceptionV3 CNN model appeared suitable for modeling this dataset.

Dataset Used: Pistachio Dataset

Dataset ML Model: Binary classification with numerical features

Dataset Reference: https://www.muratkoklu.com/datasets/

One source of potential performance benchmarks: https://doi.org/10.23751/pn.v23i2.9686

The HTML formatted report can be found here on GitHub.

Binary-Class Image Classification Model for Pistachio Identification Using TensorFlow Take 4

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: The project aims to construct a predictive model using various machine learning algorithms and document the end-to-end steps using a template. The Pistachio Identification dataset is a binary-class modeling situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: Pistachio nut has an important place in the agricultural economy; the efficiency of post-harvest industrial processes is crucial to maintaining its economic value. The industry needs new methods and technologies for separating and classifying pistachios to provide this efficiency. In this study, the research team aimed to develop a classification model different from traditional separation methods based on image processing and artificial intelligence techniques.

A computer vision system (CVS) has been developed to distinguish two species of pistachios with different characteristics that address additional market types. The research team took 2148 sample images for these two kinds of pistachios with a high-resolution camera. They applied image processing, segmentation, and feature extraction techniques to the images of the pistachio samples.

ANALYSIS: The EfficientNetV2S model’s performance achieved an accuracy score of 95.93% after 5 epochs using a separate validation dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 97.44%.

CONCLUSION: In this iteration, the TensorFlow EfficientNetV2S CNN model appeared suitable for modeling this dataset.

Dataset Used: Pistachio Dataset

Dataset ML Model: Binary classification with numerical features

Dataset Reference: https://www.muratkoklu.com/datasets/

One source of potential performance benchmarks: https://doi.org/10.23751/pn.v23i2.9686

The HTML formatted report can be found here on GitHub.

Binary-Class Image Classification Model for Pistachio Identification Using TensorFlow Take 3

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: The project aims to construct a predictive model using various machine learning algorithms and document the end-to-end steps using a template. The Pistachio Identification dataset is a binary-class modeling situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: Pistachio nut has an important place in the agricultural economy; the efficiency of post-harvest industrial processes is crucial to maintaining its economic value. The industry needs new methods and technologies for separating and classifying pistachios to provide this efficiency. In this study, the research team aimed to develop a classification model different from traditional separation methods based on image processing and artificial intelligence techniques.

A computer vision system (CVS) has been developed to distinguish two species of pistachios with different characteristics that address additional market types. The research team took 2148 sample images for these two kinds of pistachios with a high-resolution camera. They applied image processing, segmentation, and feature extraction techniques to the images of the pistachio samples.

ANALYSIS: The VGG19 model’s performance achieved an accuracy score of 92.20% after 5 epochs using a separate validation dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 95.34%.

CONCLUSION: In this iteration, the TensorFlow VGG19 CNN model appeared suitable for modeling this dataset.

Dataset Used: Pistachio Dataset

Dataset ML Model: Binary classification with numerical features

Dataset Reference: https://www.muratkoklu.com/datasets/

One source of potential performance benchmarks: https://doi.org/10.23751/pn.v23i2.9686

The HTML formatted report can be found here on GitHub.

Binary-Class Image Classification Model for Pistachio Identification Using TensorFlow Take 2

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: The project aims to construct a predictive model using various machine learning algorithms and document the end-to-end steps using a template. The Pistachio Identification dataset is a binary-class modeling situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: Pistachio nut has an important place in the agricultural economy; the efficiency of post-harvest industrial processes is crucial to maintaining its economic value. The industry needs new methods and technologies for separating and classifying pistachios to provide this efficiency. In this study, the research team aimed to develop a classification model different from traditional separation methods based on image processing and artificial intelligence techniques.

A computer vision system (CVS) has been developed to distinguish two species of pistachios with different characteristics that address additional market types. The research team took 2148 sample images for these two kinds of pistachios with a high-resolution camera. They applied image processing, segmentation, and feature extraction techniques to the images of the pistachio samples.

ANALYSIS: The DenseNet201 model’s performance achieved an accuracy score of 97.96% after 5 epochs using a separate validation dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 94.87%.

CONCLUSION: In this iteration, the TensorFlow DenseNet201 CNN model appeared suitable for modeling this dataset.

Dataset Used: Pistachio Dataset

Dataset ML Model: Binary classification with numerical features

Dataset Reference: https://www.muratkoklu.com/datasets/

One source of potential performance benchmarks: https://doi.org/10.23751/pn.v23i2.9686

The HTML formatted report can be found here on GitHub.

Binary-Class Image Classification Model for Pistachio Identification Using TensorFlow Take 1

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: The project aims to construct a predictive model using various machine learning algorithms and document the end-to-end steps using a template. The Pistachio Identification dataset is a binary-class modeling situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: Pistachio nut has an important place in the agricultural economy; the efficiency of post-harvest industrial processes is crucial to maintaining its economic value. The industry needs new methods and technologies for separating and classifying pistachios to provide this efficiency. In this study, the research team aimed to develop a classification model different from traditional separation methods based on image processing and artificial intelligence techniques.

A computer vision system (CVS) has been developed to distinguish two species of pistachios with different characteristics that address additional market types. The research team took 2148 sample images for these two kinds of pistachios with a high-resolution camera. They applied image processing, segmentation, and feature extraction techniques to the images of the pistachio samples.

ANALYSIS: The ResNet50V2 model’s performance achieved an accuracy score of 97.50% after 5 epochs using a separate validation dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 96.97%.

CONCLUSION: In this iteration, the TensorFlow ResNet50V2 CNN model appeared suitable for modeling this dataset.

Dataset Used: Pistachio Dataset

Dataset ML Model: Binary classification with numerical features

Dataset Reference: https://www.muratkoklu.com/datasets/

One source of potential performance benchmarks: https://doi.org/10.23751/pn.v23i2.9686

The HTML formatted report can be found here on GitHub.

Erika Andersen on Be Bad First, Part 9

In the book, Be Bad First: Get Good at Things Fast to Stay Ready for the Future, Erika Andersen shares her mindset and techniques for learning new things well and quickly.

These are some of my favorite concepts and takeaways from reading the book.

Chapter 8: Slaying Your Personal Dragons: One the Road to Mastery

In this chapter, Erika Andersen discusses some of the personal challenges we will face when we try to become high-payoff, Michelangelo-style learners. She offers the following observations and recommendations for us to think about:

For questions on Neutral Self-Awareness:

Q: I think I’m better than others give me credit for. Maybe they’re just not seeing what I’m capable of.

A: We could be correct; however, there is more likely another issue at play here. We may be confusing our current capability with our potential. When other people assess us based on what they see us doing right now, we often create a gap where we evaluate ourselves based on what we believe we can do.

Find someone who thinks a particular skill is not a strength of ours and, we consider, is trustworthy. Ask the person to describe the difference between how she sees us performing and what she would consider “good.” Accurately distinguishing between “what I can do now” and “what I might be capable of” is key to neutral self-awareness.

Q: How can I have an accurate sense of how good I am at something I don’t know anything about yet?

A: Good feedback sources have three essential qualities: they see us, want the best for us, and are willing, to be honest with us. There is one other quality to look for when asking a source to assess us in an area where we are a true novice. That person needs to have some expertise in that area. That way, she can compare our current skill level to her understanding of what “good” looks like and tell us how big the gap is.

Q: Okay, I’m embarrassed. I’ve just gotten some feedback, and it looks like I’m not as good at something as I thought I was. What do I do now?

A: This is where the need for neutral self-awareness combines with the need to be willing to “be bad at first” – and shifting our self-talk is key to both. Once we realize we are less good at something than we thought, we can formulate more constructive self-talk. That self-talk needs to accept our negative feelings in response to the feedback. It then can help us move through the negative feedback and on the way to hopefulness and a focus on learning.

Q: I graded myself really hard – it’s difficult to acknowledge my strengths. How can I change that?

A: We do not have to put up with our own unfair, ungenerous, unkind assessments of ourselves. We can “talk back” to that negative voice and stand up for ourselves the same way a good friend or loving family member would. We can shift our self-talk to support our success.