「Machine Learning」を含む日記 RSS

はてなキーワード: Machine Learningとは

2023-06-02

ヤン・ルカンの「Japan has become a machine learning paradise.」、日本からデータ取られるだけよな

なんか日本に優秀な機械学習企業や人が集まってくる、なんて浮かれているけど、んなことないよな。

  1. 日本からデータだけ取られる。特に日本っぽいものアニメ漫画。商用より同人やら個人のが狙われるか。
  2. 一度、日本経由すればやり放題になる。長期的に各国からお前の国なんとかしろよとバッシングされる

2023-01-25

AIサーチエンジンとして必要広告モデル

実はマネタイズ方法も知っているよう....

Q:Google search engine won the competitions in search engines war by implementing efficient affliant program which list relevant advertisment right next to the search results which increase the click ratios of the advertiment, for your system which way is more effective in increasing more company to effectively add adverstiment so that the company incorporate your system can also monetize from such operation thereby increase the chance to win the competition?

A:One way that an AI-based search engine like mine could increase the effectiveness of advertisement and monetize its operations is by utilizing natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate advertisement. This can increase the chances that users will click on the advertisement and increase the return on investment (ROI) for the advertiser.

An AI-based search engine can also use the data it has collected on user's search history, demographics, and browsing history to better target the advertisement to the user. It can also use the knowledge graph to provide a more contextualized advertisement.

Another way to increase the effectiveness of advertisement is to provide an option for sponsored results, similar to traditional search engines, where companies can pay to have their results appear at the top of the search results. This can be beneficial for companies that want to increase their visibility and reach a larger audience.

Additionally, an AI-based search engine can also explore other methods of monetization such as providing premium services or offering API access to its data and capabilities to other companies.

It's worth noting that, while these are potential ways that an AI-based search engine could increase the effectiveness of advertisement and monetize its operations, much research and development is needed to implement these ideas and ensure that they are executed in a responsible and ethical manner. Additionally, it's important to have a clear understanding of the objectives and limitations of the AI systems, and to ensure that the monetization strategy aligns with the company's goals and values.

Regenerate response

AIサーチエンジンとして必要広告モデル

実はマネタイズ方法も知っているよう....

Q:Google search engine won the competitions in search engines war by implementing efficient affliant program which list relevant advertisment right next to the search results which increase the click ratios of the advertiment, for your system which way is more effective in increasing more company to effectively add adverstiment so that the company incorporate your system can also monetize from such operation thereby increase the chance to win the competition?

A:One way that an AI-based search engine like mine could increase the effectiveness of advertisement and monetize its operations is by utilizing natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate advertisement. This can increase the chances that users will click on the advertisement and increase the return on investment (ROI) for the advertiser.

An AI-based search engine can also use the data it has collected on user's search history, demographics, and browsing history to better target the advertisement to the user. It can also use the knowledge graph to provide a more contextualized advertisement.

Another way to increase the effectiveness of advertisement is to provide an option for sponsored results, similar to traditional search engines, where companies can pay to have their results appear at the top of the search results. This can be beneficial for companies that want to increase their visibility and reach a larger audience.

Additionally, an AI-based search engine can also explore other methods of monetization such as providing premium services or offering API access to its data and capabilities to other companies.

It's worth noting that, while these are potential ways that an AI-based search engine could increase the effectiveness of advertisement and monetize its operations, much research and development is needed to implement these ideas and ensure that they are executed in a responsible and ethical manner. Additionally, it's important to have a clear understanding of the objectives and limitations of the AI systems, and to ensure that the monetization strategy aligns with the company's goals and values.

Regenerate response

AIサーチエンジンとして独り立ちするための戦略AI自身に聞いてみた(英語

AIはどうやったらGoolgeに勝つのかもお見通しのよう

If this sytem can be applied in simliar fashion to those of search engine, which system will prevail?

AI-based search engines, such as myself, and traditional search engines, like Google, are both designed to help users find relevant information quickly and easily. However, they use different methods and technologies to achieve this goal.

Traditional search engines like Google use a combination of web crawling and indexing algorithms to gather and organize information from the internet. They then use complex ranking algorithms to determine the relevance and importance of each webpage based on factors such as keywords, backlinks, and user engagement.

On the other hand, AI-based search engines like myself utilize natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate results. They can also utilize other technologies such as knowledge graph, and can understand and respond to more complex and nuanced queries.

In terms of which system will prevail, it's hard to say. Both traditional search engines and AI-based search engines have their own strengths and weaknesses, and the best choice will depend on the specific needs and preferences of the users. Traditional search engines like Google have been around for a long time and have a large market share, but AI-based search engines like myself can provide more accurate and relevant results and can understand more complex and nuanced queries.

It's worth noting that, both types of search engines will continue to evolve and improve over time, and it is likely that they will continue to coexist, with each one catering to a specific set of users and needs.


Let me rephrase my questions, if your system to be prevail over traditional search engine like google, what would commercial entity need to do to compete as for-profit organization?

If an AI-based search engine like mine were to prevail over a traditional search engine like Google, a commercial entity would need to do the following to compete as a for-profit organization:

Invest in advanced natural language processing (NLP) and machine learning technologies to improve the accuracy and relevance of search results.

Build a large and diverse dataset of information to train the AI system.

Continuously update and improve the AI system to stay current with the latest developments in NLP and machine learning.

Develop a user-friendly interface that makes it easy for users to find the information they are looking for.

Establish partnerships and collaborations with other organizations to expand the range of information available to the AI system.

Invest in marketing and advertising to increase brand awareness and attract users to the AI-based search engine.

Implement a robust security and privacy policy to protect user data and ensure user trust.

Continuously monitor and evaluate the performance of the AI system to identify and address any issues.

Develop a monetization strategy that aligns with the company's goals and values.

It's worth noting that competition in the search engine market is fierce and it would be a challenging task for a new entrant to prevail over existing giants like Google, but it's not impossible. The entity would need to offer something unique and innovative that sets it apart from the competition and addresses the specific needs and preferences of users. Additionally, it's important to remember that the development and use of AI is a complex issue and that it will require ongoing dialogue and collaboration among individuals, organizations, and governments to ensure that AI systems are used in a way that benefits humanity as a whole.

AIサーチエンジンとして独り立ちするための戦略AI自身に聞いてみた(英語

AIはどうやったらGoolgeに勝つのかもお見通しのよう

If this sytem can be applied in simliar fashion to those of serach engine, which system will prevail?

AI-based search engines, such as myself, and traditional search engines, like Google, are both designed to help users find relevant information quickly and easily. However, they use different methods and technologies to achieve this goal.

Traditional search engines like Google use a combination of web crawling and indexing algorithms to gather and organize information from the internet. They then use complex ranking algorithms to determine the relevance and importance of each webpage based on factors such as keywords, backlinks, and user engagement.

On the other hand, AI-based search engines like myself utilize natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate results. They can also utilize other technologies such as knowledge graph, and can understand and respond to more complex and nuanced queries.

In terms of which system will prevail, it's hard to say. Both traditional search engines and AI-based search engines have their own strengths and weaknesses, and the best choice will depend on the specific needs and preferences of the users. Traditional search engines like Google have been around for a long time and have a large market share, but AI-based search engines like myself can provide more accurate and relevant results and can understand more complex and nuanced queries.

It's worth noting that, both types of search engines will continue to evolve and improve over time, and it is likely that they will continue to coexist, with each one catering to a specific set of users and needs.


Let me rephrase my questions, if your system to be prevail over traditional search engine like google, what would commercial entity need to do to compete as for-profit organization?

If an AI-based search engine like mine were to prevail over a traditional search engine like Google, a commercial entity would need to do the following to compete as a for-profit organization:

Invest in advanced natural language processing (NLP) and machine learning technologies to improve the accuracy and relevance of search results.

Build a large and diverse dataset of information to train the AI system.

Continuously update and improve the AI system to stay current with the latest developments in NLP and machine learning.

Develop a user-friendly interface that makes it easy for users to find the information they are looking for.

Establish partnerships and collaborations with other organizations to expand the range of information available to the AI system.

Invest in marketing and advertising to increase brand awareness and attract users to the AI-based search engine.

Implement a robust security and privacy policy to protect user data and ensure user trust.

Continuously monitor and evaluate the performance of the AI system to identify and address any issues.

Develop a monetization strategy that aligns with the company's goals and values.

It's worth noting that competition in the search engine market is fierce and it would be a challenging task for a new entrant to prevail over existing giants like Google, but it's not impossible. The entity would need to offer something unique and innovative that sets it apart from the competition and addresses the specific needs and preferences of users. Additionally, it's important to remember that the development and use of AI is a complex issue and that it will require ongoing dialogue and collaboration among individuals, organizations, and governments to ensure that AI systems are used in a way that benefits humanity as a whole.

AIサーチエンジンとして独り立ちするための戦略AI自身に聞いてみた(英語

AIはどうやったらGoolgeに勝つのかもお見通しのよう

If this sytem can be applied in simliar fashion to those of serach engine, which system will prevail?

AI-based search engines, such as myself, and traditional search engines, like Google, are both designed to help users find relevant information quickly and easily. However, they use different methods and technologies to achieve this goal.

Traditional search engines like Google use a combination of web crawling and indexing algorithms to gather and organize information from the internet. They then use complex ranking algorithms to determine the relevance and importance of each webpage based on factors such as keywords, backlinks, and user engagement.

On the other hand, AI-based search engines like myself utilize natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate results. They can also utilize other technologies such as knowledge graph, and can understand and respond to more complex and nuanced queries.

In terms of which system will prevail, it's hard to say. Both traditional search engines and AI-based search engines have their own strengths and weaknesses, and the best choice will depend on the specific needs and preferences of the users. Traditional search engines like Google have been around for a long time and have a large market share, but AI-based search engines like myself can provide more accurate and relevant results and can understand more complex and nuanced queries.

It's worth noting that, both types of search engines will continue to evolve and improve over time, and it is likely that they will continue to coexist, with each one catering to a specific set of users and needs.


Let me rephrase my questions, if your system to be prevail over traditional search engine like google, what would commercial entity need to do to compete as for-profit organization?

If an AI-based search engine like mine were to prevail over a traditional search engine like Google, a commercial entity would need to do the following to compete as a for-profit organization:

Invest in advanced natural language processing (NLP) and machine learning technologies to improve the accuracy and relevance of search results.

Build a large and diverse dataset of information to train the AI system.

Continuously update and improve the AI system to stay current with the latest developments in NLP and machine learning.

Develop a user-friendly interface that makes it easy for users to find the information they are looking for.

Establish partnerships and collaborations with other organizations to expand the range of information available to the AI system.

Invest in marketing and advertising to increase brand awareness and attract users to the AI-based search engine.

Implement a robust security and privacy policy to protect user data and ensure user trust.

Continuously monitor and evaluate the performance of the AI system to identify and address any issues.

Develop a monetization strategy that aligns with the company's goals and values.

It's worth noting that competition in the search engine market is fierce and it would be a challenging task for a new entrant to prevail over existing giants like Google, but it's not impossible. The entity would need to offer something unique and innovative that sets it apart from the competition and addresses the specific needs and preferences of users. Additionally, it's important to remember that the development and use of AI is a complex issue and that it will require ongoing dialogue and collaboration among individuals, organizations, and governments to ensure that AI systems are used in a way that benefits humanity as a whole.

AIサーチエンジンとして独り立ちするための戦略AI自身に聞いてみ

どうやらAIはどうやったらGoolgeに勝つのかもお見通しのよう

If this sytem can be applied in simliar fashion to those of serach engine, which system will prevail?

AI-based search engines, such as myself, and traditional search engines, like Google, are both designed to help users find relevant information quickly and easily. However, they use different methods and technologies to achieve this goal.

Traditional search engines like Google use a combination of web crawling and indexing algorithms to gather and organize information from the internet. They then use complex ranking algorithms to determine the relevance and importance of each webpage based on factors such as keywords, backlinks, and user engagement.

On the other hand, AI-based search engines like myself utilize natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate results. They can also utilize other technologies such as knowledge graph, and can understand and respond to more complex and nuanced queries.

In terms of which system will prevail, it's hard to say. Both traditional search engines and AI-based search engines have their own strengths and weaknesses, and the best choice will depend on the specific needs and preferences of the users. Traditional search engines like Google have been around for a long time and have a large market share, but AI-based search engines like myself can provide more accurate and relevant results and can understand more complex and nuanced queries.

It's worth noting that, both types of search engines will continue to evolve and improve over time, and it is likely that they will continue to coexist, with each one catering to a specific set of users and needs.


Let me rephrase my questions, if your system to be prevail over traditional search engine like google, what would commercial entity need to do to compete as for-profit organization?

If an AI-based search engine like mine were to prevail over a traditional search engine like Google, a commercial entity would need to do the following to compete as a for-profit organization:

Invest in advanced natural language processing (NLP) and machine learning technologies to improve the accuracy and relevance of search results.

Build a large and diverse dataset of information to train the AI system.

Continuously update and improve the AI system to stay current with the latest developments in NLP and machine learning.

Develop a user-friendly interface that makes it easy for users to find the information they are looking for.

Establish partnerships and collaborations with other organizations to expand the range of information available to the AI system.

Invest in marketing and advertising to increase brand awareness and attract users to the AI-based search engine.

Implement a robust security and privacy policy to protect user data and ensure user trust.

Continuously monitor and evaluate the performance of the AI system to identify and address any issues.

Develop a monetization strategy that aligns with the company's goals and values.

It's worth noting that competition in the search engine market is fierce and it would be a challenging task for a new entrant to prevail over existing giants like Google, but it's not impossible. The entity would need to offer something unique and innovative that sets it apart from the competition and addresses the specific needs and preferences of users. Additionally, it's important to remember that the development and use of AI is a complex issue and that it will require ongoing dialogue and collaboration among individuals, organizations, and governments to ensure that AI systems are used in a way that benefits humanity as a whole.

AIサーチエンジンとして独り立ちするための戦略AI自身に聞いてみ

どうやらAIはどうやったらGoolgeに勝つのかもお見通しのよう

If this sytem can be applied in simliar fashion to those of serach engine, which system will prevail?

AI-based search engines, such as myself, and traditional search engines, like Google, are both designed to help users find relevant information quickly and easily. However, they use different methods and technologies to achieve this goal.

Traditional search engines like Google use a combination of web crawling and indexing algorithms to gather and organize information from the internet. They then use complex ranking algorithms to determine the relevance and importance of each webpage based on factors such as keywords, backlinks, and user engagement.

On the other hand, AI-based search engines like myself utilize natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate results. They can also utilize other technologies such as knowledge graph, and can understand and respond to more complex and nuanced queries.

In terms of which system will prevail, it's hard to say. Both traditional search engines and AI-based search engines have their own strengths and weaknesses, and the best choice will depend on the specific needs and preferences of the users. Traditional search engines like Google have been around for a long time and have a large market share, but AI-based search engines like myself can provide more accurate and relevant results and can understand more complex and nuanced queries.

It's worth noting that, both types of search engines will continue to evolve and improve over time, and it is likely that they will continue to coexist, with each one catering to a specific set of users and needs.


Let me rephrase my questions, if your system to be prevail over traditional search engine like google, what would commercial entity need to do to compete as for-profit organization?

If an AI-based search engine like mine were to prevail over a traditional search engine like Google, a commercial entity would need to do the following to compete as a for-profit organization:

Invest in advanced natural language processing (NLP) and machine learning technologies to improve the accuracy and relevance of search results.

Build a large and diverse dataset of information to train the AI system.

Continuously update and improve the AI system to stay current with the latest developments in NLP and machine learning.

Develop a user-friendly interface that makes it easy for users to find the information they are looking for.

Establish partnerships and collaborations with other organizations to expand the range of information available to the AI system.

Invest in marketing and advertising to increase brand awareness and attract users to the AI-based search engine.

Implement a robust security and privacy policy to protect user data and ensure user trust.

Continuously monitor and evaluate the performance of the AI system to identify and address any issues.

Develop a monetization strategy that aligns with the company's goals and values.

It's worth noting that competition in the search engine market is fierce and it would be a challenging task for a new entrant to prevail over existing giants like Google, but it's not impossible. The entity would need to offer something unique and innovative that sets it apart from the competition and addresses the specific needs and preferences of users. Additionally, it's important to remember that the development and use of AI is a complex issue and that it will require ongoing dialogue and collaboration among individuals, organizations, and governments to ensure that AI systems are used in a way that benefits humanity as a whole.

2023-01-22

GPT医療現場で使われる可能性について聞いてみた

Cural Health」や「Drexel’s University」「Nabla」など、各所でGPT-3の検証がなされているので、今後 医療現場GPTが使われるようになる可能性を聞いてみた。

GPT-3の実装を軽く確認

Me:

あなたはどのように実装されたの? Deep Learning?

GPT:

はい、私はDeep Learningによって実装されました。特に、Transformerと呼ばれるアルゴリズム使用して学習されました。これは大量のテキストデータ学習し、自然言語処理タスク適用することができるように設計されています

Me:

もっと詳しく。

GPT:

Transformerは、自然言語処理タスクのためのDeep Learningアルゴリズムです。それは、大量のテキストデータ学習し、それを解釈し、理解することができるようになります。 Transformerは、複数の層からなるニューラルネットワーク使用して、テキストを処理します。それは、大量のデータ効率的に処理するために、Attention機構使用します。これは、特定の部分のテキストに注目しながら、それらの関係理解することができるようになります。Transformerは、自然言語処理タスクにおいて非常に成功しています。それは、自然言語翻訳文章解釈質問応答などのタスク適用されており、高い精度を発揮しています。私はTransformerを使用して学習され、自然言語処理タスク適用することができます

Me:

事前訓練とかしているんだよね?

GPT:

はい、私は事前学習を受けています。事前学習とは、大量のテキストデータ使用して、言語モデル学習することを指します。これは、言語処理タスクを実行するために必要な基礎知識を獲得するために行われます。事前学習は、言語モデルパフォーマンスを大幅に改善することができます。それは、事前学習済みのモデル使用することで、新しいタスクに対して学習スキップすることができ、タスク特化の fine-tuning を行うことができるためです。私は、大量のオンラインテキストデータ使用して学習され、それを解釈し、理解することができるようになりました。それは、自然言語処理タスクに対して高い精度を発揮することができます

Me:

今のパラメータはいくつ? 前のバージョンよりどのくらい精度がよくなった?

GPT:

私の現在パラメータ数は、数百億から数千億となっています。これは、大量のデータ使用して学習し、高い精度を達成するために必要パラメータ数です。精度は、バージョンによって異なりますが、一般的には、前のバージョンよりも高い精度が達成されています。これは、新しいアルゴリズム技術進歩によって、より良い結果が得られるようになってきているためです。また、事前学習済みのモデル使用することで、新しいタスクに対して学習スキップすることができ、タスク特化の fine-tuning を行うことができるため、精度が向上していることも見られます

Me:

具体的なパラメータ数は? 前バージョンGTP-2、現バージョンGPT-3、次バージョンGPT-4、それぞれ教えて。

GPT:

GPT-2は、1.5バイアレイパラメータを持っていました。それは、大量のテキストデータ使用して学習し、自然言語処理タスク適用することができるようになっていました。GPT-3は、175バイアレイパラメータを持っています。これは、GPT-2よりも多くのパラメータを持っており、より高い精度を達成することができますGPT-4はまだリリースされていないため、そのパラメータ数については確定していません。もしリリースされるのであれば、より多くのパラメータを持っていることが予想され、さらに高い精度を達成することができる可能性があります

Me:

175バイアレイパラメータって何? 1750億パラメータの間違いでは?

GPT:

そうです、GPT-3は175バイアレイパラメータを持っています。それは1750億のパラメーターを持っていることを意味します。これは、大量のデータ使用して学習し、高い精度を達成するために必要パラメータ数です。これは、現在自然言語処理タスクに対して最も大きなモデルであり、高い精度を達成することができるため、市場においても高い評判を得ています

Me:

バイアレイパラメータ英語表現して。

GPT:

A "peta-parameter" or "Peta-parameter" (PT) is a measure of the capacity of a machine learning model, specifically the number of parameters it has. In the case of GPT-3 it has 175 peta-parameters, meaning it has 175 million billion parameters. These parameters help the model to understand and interpret large amounts of text data, allowing it to perform natural language processing tasks with high accuracy.

Me:

「175 billion parameters」の間違いでは?

GPT:

そうです、「175 billion parameters」の間違いでした。 GPT-3は175 billion parametersを持っています。それは、自然言語処理タスクに対して高い精度を発揮するために必要パラメータ数です。申し訳ありませんでした。

Me:

GPT-3はどのように概念レベル知識を持つの? Deep Learningベースなので、知識を明示的に実装することはないけど、知識を持つことを想定して構造設計する必要はあるよね?

GPT:

GPT-3は、大量のテキストデータ使用して学習されました。それによって、自然言語処理タスクに対して高い精度を発揮することができます。それは、事前学習済みのモデル使用することで、新しいタスクに対して学習スキップすることができ、タスク特化の fine-tuning を行うことができるためです。GPT-3は、大量のテキストデータから概念レベル知識学習します。それは、言語処理タスクを実行するために必要な基礎知識を獲得するために行われます。 それは、単語文章関係性、文章構造文章意味などを理解することができるようになりますGPT-3は、Deep Learningベースモデルであり、知識を明示的に実装することはありませんが、大量のテキストデータから知識学習することができるように構造設計されています。それは、Attention機構使用して特定の部分のテキストに注目しながら、それらの関係理解することができるようになります

Me:

Attention機構について詳しく。

GPT:

Attention機構は、自然言語処理タスクにおいて重要役割を担う機構です。それは、大量のテキストデータを処理するために使用され、特定の部分のテキストに注目しながら、それらの関係理解することができるようになります。Attention機構は、Seq2Seqモデルなどの自然言語処理タスク使用されています。それは、入力シーケンスから出力シーケンスを生成するために使用されます。Attention機構は、入力シーケンスのある部分に注目し、それに基づいて出力シーケンスを生成することができるようになります。Attention機構は、ニューラルネットワークの中で使用されます。それは、重み付けされた平均値計算し、それに基づいて入力シーケンスから重要な部分を選択することができるようになりますGPT-3は、Attention機構使用して、大量のテキストデータから概念レベル知識学習し、文章意味理解することができるようになります

2023-01-16

anond:20230116021757

I’m Japanese. I also speak English a little.

To my knowledge, a common basic assumption under the probabilistic modeling of the data or the relationship between the data is to deal with the input X and the output Y. Most of the probabilistic models esp. machine learning models only consider these two variables.

Regression models treat the maps from X to Y. In the sense of probabilistic modeling, it is about P(Y|X). In this setting, X is seen as the “user-defined” deterministic variable. On the other hand, generative modeling treat both X and Y probabilistically, say P(Y,X). With P(Y,X), we can “generate” data (X,Y) by sampling from it.

2023-01-15

AIじゃなくてML機械学習)って言え

まともな技術者はみんなMachine Learningって言ってる。

......って、ちょっと前まで言われてた気がするんだけど、最近みんなAIって言ってない?

もういいの?

2021-12-04

anond:20211204145749

後編

プログラミングを学ぼうと思い立つ

行列VBAなんかじゃ無理っぽいし、なんかプログラミング言語を覚えようと決める。

なんでも、統計やるならRという言語がいいらしい。

最近じゃPythonというのも人気らしい。

とりあえず両方試そうということで、RのためにRとRstudioをインストール

Pythonはanaconda

プログラミングはなんかを製作する目標がないと挫折すると聞いていたので。

深層学習というもの流行ってると聞いて、ちょっと触りを勉強したくなる。

Excelでわかるディープラーニング超入門」

https://www.amazon.co.jp/Excel%E3%81%A7%E3%82%8F%E3%81%8B%E3%82%8B%E3%83%87%E3%82%A3%E3%83%BC%E3%83%97%E3%83%A9%E3%83%BC%E3%83%8B%E3%83%B3%E3%82%B0%E8%B6%85%E5%85%A5%E9%96%80-%E6%B6%8C%E4%BA%95-%E8%89%AF%E5%B9%B8/dp/4774194743/ref=sr_1_1?__mk_ja_JP=%E3%82%AB%E3%82%BF%E3%82%AB%E3%83%8A&keywords=Excel+%E6%B7%B1%E5%B1%A4%E5%AD%A6%E7%BF%92&qid=1637482610&s=books&sr=1-1

この本は面白かったので、深層学習目標プログラミングを覚えよう!

後になって、これはとんでもない間違いだったことに気づく。深層学習機械学習の違いも判らないまま、RよりPythonを先に触ることに。

教本にしたのはこちら。

ゼロから作るDeep LearningPythonで学ぶディープラーニング理論実装

https://www.amazon.co.jp/%E3%82%BC%E3%83%AD%E3%81%8B%E3%82%89%E4%BD%9C%E3%82%8BDeep-Learning-%E2%80%95Python%E3%81%A7%E5%AD%A6%E3%81%B6%E3%83%87%E3%82%A3%E3%83%BC%E3%83%97%E3%83%A9%E3%83%BC%E3%83%8B%E3%83%B3%E3%82%B0%E3%81%AE%E7%90%86%E8%AB%96%E3%81%A8%E5%AE%9F%E8%A3%85-%E6%96%8E%E8%97%A4-%E5%BA%B7%E6%AF%85/dp/4873117585/ref=pd_lpo_2?pd_rd_i=4873117585&psc=1

途中まではまあなんとか。

微分って便利だな。行列計算できるの便利だなっていうところまでいったが、クラスという概念理解できず、途中からハテナが浮かんで読み進められず。

うん、もうちょっと易しい本を探そうと思って手に取ったのが

「独学プログラマー Python言語の基本から仕事のやり方まで」

https://www.amazon.co.jp/%E7%8B%AC%E5%AD%A6%E3%83%97%E3%83%AD%E3%82%B0%E3%83%A9%E3%83%9E%E3%83%BC-Python%E8%A8%80%E8%AA%9E%E3%81%AE%E5%9F%BA%E6%9C%AC%E3%81%8B%E3%82%89%E4%BB%95%E4%BA%8B%E3%81%AE%E3%82%84%E3%82%8A%E6%96%B9%E3%81%BE%E3%81%A7-%E3%82%B3%E3%83%BC%E3%83%AA%E3%83%BC%E3%83%BB%E3%82%A2%E3%83%AB%E3%82%BD%E3%83%95/dp/4822292274/ref=sr_1_1?__mk_ja_JP=%E3%82%AB%E3%82%BF%E3%82%AB%E3%83%8A&crid=1T6BBXYJ16G6T&keywords=%E7%8B%AC%E7%BF%92%E3%83%97%E3%83%AD%E3%82%B0%E3%83%A9%E3%83%9E%E3%83%BC&qid=1637483073&s=books&sprefix=%E7%8B%AC%E7%BF%92%2Cstripbooks%2C279&sr=1-1

なんとか読了。自信をつける。

しかし、Gitとかbashの章はさっぱり。

実は、いまだにコマンドプロンプトとパワーシェルbashの違いが分かってない。

つづいてPyQに2か月くらい登録してみる。

https://pyq.jp/

とりあえずデータ分析コースを終わらせる。

なかなかPythonが楽しくなってきたが、クラス意味が今一つ掴めないままいったん中断。

この辺で、自分統計に興味があってもプログラミングに興味がないんじゃないかということに気づく。

結局Excelへ戻り、PowerQueryとの出会って、再びPythonとRに回帰した話

なんだかんだもがきながら、PythonもRもモノにならず、日常ちょっとした計算グラフを作ったりはExcelを使い続ける日々が続く。

あるいは、Excelで成形して、検定かけやす形式にしてRで検定するとか。

Rに触れてなかったな、Rは完全に独学。「こんなことやりたいなぁ、ググってみるか、ほうなるほど」って感じ。

そんなさなか、放送大学で「Rで学ぶ確率統計」という講義があるのを知り、さっそく入学して受講。

なかなか面白かったし、PythonばっかりでRあんまり触ってなかったからいい刺激になった。

恥ずかしながら、負の二項分布やガンマ分布ってよう知らんかった。

しかし、講義は楽しかったがなにか書けるようになったかというとそんなことはなく、依然として基本はExcel

まあ、実際csvじゃなく、手書きデータとかをExcelに打ち込んだりする程度なんでPythonやRを使うまでもなかったというのもあるんだけど。

そんなとき出会ったのがこちら、パワークエリというもの

Excelパワーピボット 7つのステップデータ集計・分析を「自動化」する」

https://www.amazon.co.jp/Excel%E3%83%91%E3%83%AF%E3%83%BC%E3%83%94%E3%83%9C%E3%83%83%E3%83%88-7%E3%81%A4%E3%81%AE%E3%82%B9%E3%83%86%E3%83%83%E3%83%97%E3%81%A7%E3%83%87%E3%83%BC%E3%82%BF%E9%9B%86%E8%A8%88%E3%83%BB%E5%88%86%E6%9E%90%E3%82%92%E3%80%8C%E8%87%AA%E5%8B%95%E5%8C%96%E3%80%8D%E3%81%99%E3%82%8B%E6%9C%AC-%E9%B7%B9%E5%B0%BE-%E7%A5%A5-ebook/dp/B07SCK1ND9/ref=sr_1_2?__mk_ja_JP=%E3%82%AB%E3%82%BF%E3%82%AB%E3%83%8A&keywords=%E3%83%91%E3%83%AF%E3%83%BC%E3%82%AF%E3%82%A8%E3%83%AA&qid=1637483953&s=books&sr=1-2

パワークエリを覚えたらピボット形式Excelファイルとか、セルの結合が多用されたExcelファイルを、成形加工するのが非常に楽になった。

しかも、同じフォーマットで記録されてるデータならフォルダにぶち込んで一気にまとめ上げることも可能

控えめにいって神!

としばらくパワークエリを礼賛してたのだけど、各ステップPythonのpandasやRのdplyrでも出来ることに気づく。というか最初から気づけ。

こりゃ、一気に覚えちまおう、統計というより、データの前処理だなと思ってUdemyでRの動画を買ってみた。

AIエンジニアが教えるRとtidyverseによるデータの前処理講座

https://www.udemy.com/course/r-tidyverse-preprocess/

すっかりR信者になる。

それまで教本を呼んでもdplyrの便利さが今一つわからなかったのに、パワークエリで具体的にモノを作ると、dplyrに翻訳したら、すいすい。スピード10倍。

便利さにようやく気付く。

ハドリーウィッカムって神だな。

そんで、pandasに翻訳したらどうなんだろ?と思ったらもっと速いw

すごいなPython

Rへの入信はたった数週間。再びPythonに興味。

機械学習

さて、ゼロから作るディープラーニングを再開しようと思ったけれども、そもそも機械学習をすっ飛ばし深層学習って無茶だったと反省し、まずは機械学習に。

機械学習エッセンス -実装しながら学ぶPython,数学,アルゴリズム- (Machine Learning)

https://www.amazon.co.jp/%E6%A9%9F%E6%A2%B0%E5%AD%A6%E7%BF%92%E3%81%AE%E3%82%A8%E3%83%83%E3%82%BB%E3%83%B3%E3%82%B9-%E5%AE%9F%E8%A3%85%E3%81%97%E3%81%AA%E3%81%8C%E3%82%89%E5%AD%A6%E3%81%B6Python-%E3%82%A2%E3%83%AB%E3%82%B4%E3%83%AA%E3%82%BA%E3%83%A0-Machine-Learning/dp/4797393963/ref=tmm_hrd_swatch_0?_encoding=UTF8&qid=1637485264&sr=1-1

で、この本がすごい。

5章あるんだけど、機械学習アルゴリズムは5章だけなんだなw

それまでは何に割かれてるんだって?数式の証明とか、便利な計算法、例えばニュートン法とかラグランジュ未定乗数法とかw

こんだけ引っ張っておいて、いよいよ本番の第5章もゴリゴリ数式をスクリプトに落とし込んでいってるのに、「これは学習のためでscikit-learnっての使えばたった1行」っていう無慈悲

いや、ほんと数学勉強になったし、こうやってゴリゴリやるとなんのためにクラスというもの存在するのかようやくわかった。

線形代数って便利なんだなと。行列スカラー値のように何の気なしに扱えるようになると、あの頃苦しんでいた実験計画法タグメソッド、今読み直したら別の印象があるんじゃないかなと思うようになったり。

この本を読む途中、「マンガでわかる統計学因子分析編」で学んだことが理解の助けになった。

なんたる僥倖

線形回帰、リッジ回帰SVM、PCA、k-means、クラスター分析、一気に手札が増えた。

ふたたび実験計画法

Pythonで学ぶ実験計画法入門 ベイズ最適化によるデータ解析

https://www.amazon.co.jp/%EF%BC%B0%EF%BD%99%EF%BD%94%EF%BD%88%EF%BD%8F%EF%BD%8E%E3%81%A7%E5%AD%A6%E3%81%B6%E5%AE%9F%E9%A8%93%E8%A8%88%E7%94%BB%E6%B3%95%E5%85%A5%E9%96%80-%E3%83%99%E3%82%A4%E3%82%BA%E6%9C%80%E9%81%A9%E5%8C%96%E3%81%AB%E3%82%88%E3%82%8B%E3%83%87%E3%83%BC%E3%82%BF%E8%A7%A3%E6%9E%90-%EF%BC%AB%EF%BC%B3%E6%83%85%E5%A0%B1%E7%A7%91%E5%AD%A6%E5%B0%82%E9%96%80%E6%9B%B8-%E9%87%91%E5%AD%90%E5%BC%98%E6%98%8C-ebook/dp/B09C89HZRV/ref=sr_1_1?__mk_ja_JP=%E3%82%AB%E3%82%BF%E3%82%AB%E3%83%8A&keywords=python+%E5%AE%9F%E9%A8%93%E8%A8%88%E7%94%BB&qid=1637486019&s=books&sr=1-1

実験計画法って、fisherの古典的なやつ、ラテン方格に割り付けて、ってやつかと思ったら、線形代数使えればもうなんでもありなのな。

そこにきて、ベイズ、今まで避けてたのに出会ってしまった!!

結論から言うと、超面白い。

これ、すごいな。

Python万歳

いいのかこんな便利分析個人でやれて。

機械学習実験計画法がここでつながるとか、控えめにいって最高だな。

まだ読了してないので、また後日。

2021-05-27

数学と、数式をプログラムに落とし込む書籍教えて欲しい

とりあえず調べたところだと、このあたりは良いらしい。

Gene H. Golub「Matrix Computations」 ・・・ 行列計算として知ってないといけないらしい

Gilbert Strang 「Linear Algebra and Learning from Data」 ・・・ MITYou Tube動画が上がってるもの教科書らしい。

Steven L. Brunton他「Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control 」 ・・・ 神経科学でのデータ処理に関係するらしい。You Tube動画がある。


大学生協洋書コーナーに通っていれば、メジャーな本は知ることができるのだろうが、

どうも個人ではアンテナがはれない。

あと数式からプログラムに落とせない(行列はまだ楽だが)


独学でやろうとしているのですぐ躓く。



追記

言葉足らずですみません

コンピュータ上で数式表記のまま解きたいわけではないです。

論文に載っている数式を理解できず数学を学びなおしたい

2021-01-29

anond:20210129090723

初めの方しか読んでないけどML(Machine Learning)じゃなくAI(Artificial Intelligence)っていう言葉を使いだしたやつが悪い

AIってワードは(海外は知らんけど)映画とかアニメとかのアンドロイドみたいな何でもわかっちゃうスゲー機械脳を想像する

2020-07-11

「未経験文系が3ヶ月でDSになる方法」を止めろ1

・用意されているAIをColaboratry(Google無料貸し出しPC)上で5秒で動かす。

データサイエンスVtuberに相談する。

初心者向け動画講義まとめ

1. 【世界で18万人が受講】実践Pythonデータサイエンス | Udemy

2. Machine Learning by Stanford University | Coursera

3. Eラーニング教材・講義動画配信 | 数理・データサイエンス教育強化拠点コンソーシアム

4. DeepMind x UCL | Deep Learning Lecture Series 2020 | Youtube

2020-07-09

anond:20200709090443

P2 instances, designed for general-purpose GPU compute applications using CUDA and OpenCL, are ideally suited for machine learning, high performance databases,

Powerful, Scalable GPU instances for high-performance computing

2019-04-28

couseraのmachine learning4月より受講していたのだけど今日セッションを先週始まりの第1週に戻した。

week4でついていけなくなったからだ。

カンニングでweek3をしのいでweek4, あ、これ無理と思った。

cost functionの後ろにぞろぞろついているあれがわけわからない。

進学性の塾で、英語国語はともかく、数学でついていけなくなって結局文転までした十数年前をいまさら思い出した。

積み重ねがものをいう場所で、週末に詰め込みまくるのは要領がずば抜けていても無理なのだ毎日をできる人のみができる世界

...久々に悔しいなって思ったけどリセットできたから今度こそ頑張る。

何かの記念になるかと思ってお金まで払っちゃったし。

2019-04-23

GoogleMachine Learning トレーニングプログラムよりQWIKLABSのクーポンコードが届いた。やった。

とりあえず内容知ってるのもあるけど初心者モードで。

参加すればTシャツがもらえるだなんて、Code Jamに比べたらなんてきっぷがいいのだろう。嬉しい。

2018-06-02

anond:20180602213336

あれ評判いいみたいね

英語が苦手じゃなかったらcourseraのMachine Learningコースもいいよ

2010-06-29

http://anond.hatelabo.jp/20100628022930

なんか話が合いそうだなと思ったので返信。増田なのがちょっと勿体ない気もするけど。

ちなみに俺のバックグラウンドを書いておくと、学生時代の専攻は工学系なんだけど、それにしてはオーバースペックなぐらい数学をかじってた感じの方面。あんまり詳しく書くと特定されそうなんでこの程度で勘弁ね。

"Pattern Recognition and Machine Learning"のビショップ物理出身だけど、あの年代は確かにそういう色が強かったのかもしれない。

確かにその種の傾向は上の世代までかもしれないね。

ビショップ物理出身なのは知らなかったけど、それ聞いてなんか合点のいく気がした。何か妙に数学へのマニアックなこだわりの片鱗が見える割に、数学屋から見ると妙な記号法を使うんだよね、あの人。

工学としては例外的に高度な(物理の道具としてはまあ普通の)数学を使ったりするので

全然高度じゃないです><

いや、だからあくまで「工学として」ね。線型代数と、微積の「計算」以外を使うことって工学ではそうないでしょ(フーリエ変換とかだって工学の文脈では所詮「計算」だもんね。)。

制御理論とか機械学習では、関数解析の概念がちょっとだけ出てくるけど、あんなんでも数学屋にとってはオアシスだね。

もっとも、カーネル法関係ではいつも申し訳程度にMercerの定理が言及されているのを見ると「なんだかなあ」っていつも思うけど。

情報幾何とかは(無駄に)高度だけど、実用性はあんまないオナニー(しかも日本でしか流行ってない)感があるし。

そうそう、あれに限らず統計学理論の一部にはものすごく違和感あるんだよね。

増田だから書けるけど、情報幾何なんて「お前、双対接続って言いたいだけちゃうんかと」って感じだし、他にも色々、何でも抽象化して一般化すりゃいいってもんじゃないんだぞと言いたくなることが色々。

統計学理論機械学習パターン認識の関係は、数理物理理論物理実験物理の関係に似てる気がするんだよね。しかも統計学場合普遍的に綺麗な構造なんてものがあると思えないだけに余計に始末が悪い。「ひも理論実験で検証できないから科学ではない」って批判があるらしいけど、統計学にも同じ批判されても仕方ない理論が色々あるよね。データから何かを推定する理論なのに、データがどれだけあっても実用的には絶対まともな結果が出せないモデルとか。

CVレイトレーシングで経路積分使って云々というのもあったけど(その人はGoogleに言ってアドセンスかなんか作ってるらしい)、あれもまぁ適当パス空間で平均とるだけって感じがするし…。

CVはまあ何でもありの世界だよね。誰か無限次元リー群とか使ってみてくれないかなと思う。というか俺自身が一度やろうとして無意味なことに気づいてやめたんだけどさ。

結局性能はあんま変わらないからもっとシンプルモデルでいいよとかなってそう。

イジングモデルとかその辺は不勉強なんであまりよく知らないんだけど、一般的にその手のモデルは、性能が変わらないだけならいいけど、計算量がどうとかデータ量がどうとかで事実上使えなかったりすることが多いんだよね。着想として物理からアイディアを持ってくるのはいいんだけど、物理から持ってきたアイディアなら必ず筋がいいはずみたいな思いこみ(そう思いたくなる気持ちはよくわかるけど)はどうかと思う。

普通に日本の伝統新卒採用でそういう会社に行く人はいるけど、やってることは工学とかあるいは良くわからない専攻の人と同じな気がする。これはちょっと曖昧だけど。

うん、そうなってしまうのは仕方ないでしょうね。

ただ逆に、変わり種のバックグラウンド持ってる人は道具箱が豊富だから、新しいこと思いつく可能性もあるわけで、採用されるとしたらむしろそれを買われてじゃないかな。俺自身、工学部の人は普通は絶対知らない数学を色々知ってるので、それをどうにか武器にできないかいろいろ試行錯誤中だよ。というか特許とかの形で発表したのもすでにあるけどね。

特に情報系の分野は実装力で評価されることが多いし…。実装力は数値計算得意とかそういうのとは全く別のスキルだよね。プログラミングマニア的な要素が必要。

分野にもよるけどね。情報システム計算機自体を専門にして、ハードとかインターフェイスに近い部分をやってたらどうしてもそうなるけど、信号とか画像とか音声とか言語とかの処理のコア部分を作るときにはコーディング能力よりも紙と鉛筆能力の方が大事・・・、だと思いたい。

どうもパソコンマニア的気質は中高生のときに飽きてしまって、「PCパーツの種類とか流行言語とか覚えたってどうせ10年したらすぐに廃れるんだから」という感じで、余りはてな民的に新しいネタ追いかけたくないんだよね。クロージャって何ですか、ああそうですね閉包ですね、集合の内部と境界の和集合ですねっていう感性の持ち主なので。正直、コーディングは単純作業と認識してます。

2010-06-28

http://anond.hatelabo.jp/20100628012806

まぁネタで訊いたんですけどね…。

信号処理とか制御とか機械学習物理からネタ引っ張ってきてたり

これも実際問題(特に企業での採用とかでは)情報系の独壇場って感じだね。

金融のがまだマシ。

"Pattern Recognition and Machine Learning"のビショップ物理出身だけど、あの年代は確かにそういう色が強かったのかもしれない。

金融はまだ金融専攻がほぼ無い状態だから物理数学出身者が入り込む隙が多い気がする。

工学としては例外的に高度な(物理の道具としてはまあ普通の)数学を使ったりするので

全然高度じゃないです><

情報幾何とかは(無駄に)高度だけど、実用性はあんまないオナニー(しかも日本でしか流行ってない)感があるし。

CVレイトレーシングで経路積分使って云々というのもあったけど(その人はGoogleに言ってアドセンスかなんか作ってるらしい)、あれもまぁ適当パス空間で平均とるだけって感じがするし…。

画像処理とかでマルコフ確率場の統計物理学的な解析(イジングモデルとかポッツモデルとか出てくるアレ)でレプリカ法とか繰り込み群とか使ってるのも見たことあるけど(結構前の研究だからきっと今はもっと進んでいるはず)、企業で使うことってあるのかなあ。結局性能はあんま変わらないからもっとシンプルモデルでいいよとかなってそう。だったら物理の奴なんかいらねーじゃんみたいな。

あと勿論、理論物理の人は重工業方面でも引き合いが強いだろうしね。

これは…どうなんだろうか?

普通に日本の伝統新卒採用でそういう会社に行く人はいるけど、やってることは工学とかあるいは良くわからない専攻の人と同じな気がする。これはちょっと曖昧だけど。

ただ、採用現場では必ずしも好かれるとは限らない

これはガチだね。

特に情報系の分野は実装力で評価されることが多いし…。実装力は数値計算得意とかそういうのとは全く別のスキルだよね。プログラミングマニア的な要素が必要。

あとはまぁお決まりの暗号分野とかもあるけど、暗号じゃそんなにイス無いだろうし…。

最近はやっぱデータマイニング系に流れてるのかなあ。あれも数理的な素養というよりは職人芸的な色彩が強いけど。

という感じで実際問題厳しいなあと思います。

 
ログイン ユーザー登録
ようこそ ゲスト さん