Gus (🤖🧠+🐍+🥑🗣️) @gusthema Twitter profile | Pikagi

Pikagi

Gus (🤖🧠+🐍+🥑🗣️)

@gusthema

21,684

Followers

1,238

Following

833

Media

13,501

Statuses

AI Developer Advocate @google - Gemma 💎 - Machine Learning 🤖🧠 - Google AI ⚙️🧠 - DevRel 🥑🗣️ find me also at:

City of London, London

Joined July 2011

Don't wanna be here? Send us removal request.

Pinned Tweet

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Machine Learning🤖🧠 can be scary for developers!😱 Let me help you with this!💪🏽 If you are a Mobile📱, Web🕸️ or Backend🖥️ developer, you can use ML from the comfort of your preferred IDE without needing the heavy math part of it! 🤩🤯

Tweet card media

Adding Machine Learning to your developer toolbox

Machine learning can be a challenging field, as there are a lot of new concepts to learn from the perspectives of mobile, web, and back-end developers. Find ...

www.youtube.com

8

28

140

Last Seen Profiles

@cottagedelight

@inkredible_h

@nikebasketball

@mmwebassist

@SlimFord314

@_MumJeans

@MazharYT

@LeoLitjens

@travieso50

@Mostalent

@Ian_y_CeCe

@arnocast

@albuquerqueof_

@sofiar388

@AnikaCir

@MECHANlCALFEVER

@denefield_

@alyamani08

@oscar6971760216

@wamza_

@Sreenat77667884

@plautistic

@EstadoAlternado

@SimonKIDS

@toushika_pamm

@MECCambridge

@rrtion

@JaeIvlie

@vidramirez_

@s__d0ri

@gamecenter_will

@itisHARIZ

@BinorRaja

@WexfordEagles

@GenV_Eng

@organzahisteria

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Imagine you need to load a very large (eg: 5.7GB) csv file to train your model!🤔 This is a very common problem in real world situations and also in many Kaggle competitions! How can we use Pandas 🐼 effectively to do that? Let's dive in… [2 effective min] 1/10🧵

28

266

1K

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

There, fixed for you

Tweet media one

40

142

1K

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Today it's my 6 year Google anniversary! I started as an android developer 📱🤖 and today I'm an ML developer 🧠🤖 I learned a lot of technical stuff (A LOT!), but there's much more than that. Let me tell you some of the things I learned... 1/11🧵

28

137

954

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

My goals for this year are to help you learn: - Python 🐍 - Machine Learning 🤖🧠 - TensorFlow 🤖🛠️ If any of these interest you, follow me so you don't miss the content! And share with your friends so they can learn too!🤝🏾

18

81

740

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

"How do I learn Python?" 🤔 3 tips: • Do one basic tutorial 🤓 • Practice, practice, practice 💪🏾 • Start/Find a project to apply what you learned 🧐 "Ok Gus, how about some links?" 👇

25

131

615

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

1 year

Oi @cauemoura e @FeCastanhari Sou muito fã de seus vídeos! Vi alguns cortes de vcs no @Podpah e entendo sua preocupação com AI. Não concordo, mas entendo Se quiserem conversar e entender o ponto de vista de alguém que trabalha nessa área todo dia, minha DM está aberta.

15

43

585

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Hi👋🏾 I'm Gus and work as a Developer Advocate on the Google AI team I share content about: 🤖🧠Machine Learning 🤖🧡TensorFlow 🐍🧑🏾‍💻Python 🥑🤝DevRel I'm almost at 16K followers! Can you help me get there? leave your intro in the comments and share to help me reach it! 🥺🥺

38

54

577

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Machine learning goes beyond Deep Learning and Neural Networks Sometimes a simpler technique might give you better results and be easier to understand A very versatile algorithm is the Decision Forest 🌴🌲🌳? What is it and how does it work? Let me tell you.. [7 min] 1/10🧵

Tweet media one

4

113

514

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Five websites to learn Python🐍 that you will want to bookmark and start your journey today 👇🏾👇🏾👇🏾

6

142

498

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Going to the office today!

Tweet media one

8

23

460

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

What is the golden rule in Machine Learning? 🤔

130

58

414

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

How can we change a 3 minute load time to 1 second? ⚡️⚡️⚡️🤯 As a Pandas🐼 user, the read_csv method might be very dear 💕to you. But even with a lot of tuning, it will still be slow. Let's make it faster!!! [1 ⚡️ min] 1/7🧵

Tweet media one

8

67

409

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Do you need a Python course to start 2023? So, here is a tip💡 for you: ➡️Learn Python with the Kaggle course: Pros: • Kaggle Kernels allows you to try the code in the browser • Very good pace of content • Fun and challenging puzzles

Learn Python Tutorials

Learn the most important language for data science.

10

105

392

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

If you code in Python🐍 for more than an hour, you probably have seen the keyword lambda In essence lambda enables us to create an anonymous function or function without a name When and why should you use it? [1 (⚡️) min] 1/5🧵

Tweet media one

8

53

340

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

I like Python🐍 because: -> Very easy to read. It looks like pseudo code -> Fast to create scripts for automating work -> Huge amount of libraries for all kinds of specific tasks (NumPy, Beautiful Soup, Pandas, TF, Pillow, Librosa) Why do (or don't 👀) you like Python? 🤔

39

37

337

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Enjoying my balcony with 🌞, a great 📖, ☕ and a 🍌 Can't complain!

Tweet media one

20

15

336

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

One word. As a Machine Learning Developer, you need to be good at ________

224

30

331

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Did you know that you can apply styles to your Pandas visualization? Let's take a brief look at it 👀 [1 min] 1/8🧵

Tweet media one

10

53

326

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

What are Python🐍 decorators🎀? Decorator is an Object Oriented pattern that allows behavior to be added to individual objects They can be more efficient than subclassing and in some cases it can make your code 1000 faster!👀🤯 [1 min] 1/5🧵

6

67

323

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

5 links to help you start (or continue) your Machine Learning journey 👇

12

75

317

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Everyone that does some Data Analysis or Machine Learning knows the Pandas library 🐼 One thing that not everyone is aware of is how to use it efficiently! Have you thought about how much memory your dataframe is using? 🤔 How to use less? 🗜️ Let me show you… [2 min] 1/8🧵

6

64

304

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

For you, what are the hardest concepts in Computer Science? 🤔 For me it's: - regular expression 😭 - dynamic programming 😵‍💫

87

17

297

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Excellent opportunity to learn Python basics and maybe charge your career! The curriculum is very interesting - Python basics - git - cloud And you get a certificate! Very good!

Google IT Certificates - Grow with Google- Grow with Google

The IT Support Certificate Training Program, developed by Google and hosted on Coursera, can help you prepare for an entry-level IT support job.

3

79

293

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

"Machine Learning is only hype!" 🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩🚩

10

35

283

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Today is my birthday! As my gift to you, I created this thread with all my NLP posts of this week to give you some technical content for your weekend! [2 minutes] 1/11🧵

32

44

284

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Hi everyone, I don't like asking but can you help me reach the magic 10K? I'm almost there! In return, I'll post daily quality content about: - Python🐍 - Machine Learning🧠🤖 - Career Development👨🏾‍🔬 Share to increase the reach!

15

46

282

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

I prefer working with a good programmer that is a nice person overall than with an amazing 10x 🧑🏽‍🎤 programmer that is an a**hole People skills matter!

15

22

259

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

⛔️: print(“Hi ” + name + “, how are you?”) ✅: print(f“Hi {name}, how are you?”) #Python

12

21

256

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

I was telling a friend that one cool feature from Python is list slice notation So instead of just posting the link I decided to do a brief explanation. [5 min] Python's regular array indexing as in multiple languages is: a[index] a = [0, 1, 2, 3, 4] a[0] == 0 1/12🧵

10

44

254

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

New year and you want to start your Machine Learning 🤖🧠 journey Here are the 3 things you'll need to start: 1⃣ - A good ML Tutorial/Course 2⃣ - An environment to code 3⃣ - The Secret sauce Let me give you some directions🎯 [1 minute] 1/7🧵

8

62

249

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

I've just completed 22 years as a developer! 🎈🥳🎂🎉🎊 These are 10 habits that helped me get here: 👇🏽

12

43

235

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Effective Pandas🐼 tip [4]: When you start to work on a real dataset with more data (millions of records) and want to run a transformation on the data, what should you do? Let me tell you how to make your execution more than 19000 times faster!! 🤯🤯🤯 [1 effective min] 1/7🧵

7

34

230

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

💡Machine Learning🤖🧠 models are designed to make predictions🎱🔮 and not giving you insights about the data! If you have a bunch of data and want to find out "interesting" things about it, use Statistical Approaches!📊📈 🧵

7

37

221

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

@tunguz Data? Yes of course we have it! They are all here in this folder called "pdfs"

5

11

220

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Today, 7 years ago, I left my country with my family to try a better life for us! It wasn't easy but I'm very happy we did it!

Tweet media one

18

3

217

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

What’s one thing in Python🐍 you’ve stopped doing as you’ve become more experienced? I'll start: 🚫 -> range(len(collection)) ✅ -> enumerate(collection)

26

10

195

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Python🐍 viz📊 libs to help you: • Matplotlib: The standard and must know! • Seaborn: prettier + easier Matplotlib • Mpld3: Matplotlib + interactive w/ D3 • Bokeh: prettier + Matplotlib + interactive • Altair: declarative stats viz • Folium: interactive map🗺️ views

9

37

193

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Are you interested in: - Machine Learning🤖🧠? - have fun?👍🏾🥳 - help the community?🤝👥 If so you should definitely look into the Google summer of code!👀 I'm one of the mentors for TensorFlow so there's a chance we can collaborate on cool projects 😉

@GoogleOSS

Google Open Source

2 years

🟩 Are you a #Developer new to open source? We've compiled a list of ways to increase your chances of being selected as a 2022 Google Summer of code Contributor. 🟨 Get application tips and learn more about the program. 👉

Tweet media one

3

73

227

5

37

186

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

How deep do you need to understand Machine Learning to start using it?🤔 Let's use an analogy to explain this Imagine 3 personas: • 🧑🏾‍✈️Driver • 👩🏾‍🔧Mechanic • 👩🏾‍🔬Car Manufacturer [1 minute] 1/5🧵

13

40

179

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

When you start reading about Machine Learning one term comes up frequently: NLP What is NLP? • Natural Language Processing • NLP = Linguistics + Computer Science + AI • The field that studies how can computers understand text Some history about it📖 [30 sec] 1/5🧵

5

39

163

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

So beautiful! Project idea: enable the lines for any performance using MoveNet!

@EvanKirstel

Evan Kirstel #B2B #TechFluencer

7 years

A computer algorithm in action #MachineLearning

41

1K

2K

2

21

164

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

If you are looking for something to learn during the weekend, How about on-device Machine Learning? You'll only need some understanding of ML and some of Mobile development. Let me give you all the pointers in FAQ style: [reading: 5.84 min] 1/12🧵

2

33

156

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

The main reason why Python🐍 is so popular with Machine Learning🤖🧠 developers is because it's so easy to read.👓 But another feature that really helps is the collections manipulation tools, specifically Slicing!🔪 Let me show you how it works 👇🏾👇🏾👇🏾 [2 min] 1/11🧵

5

33

161

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Do you want to start working with Machine Learning? Let me give you 3 tips that I used to start my journey and that helped me a lot! [2 min] 1/7🧵

3

42

161

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

@EmmaBostian Sorry Emma but I disagree. One example is that big-o is part of problem solving, otherwise you'd use brute force to solve every problem and that's not always the case.

16

0

159

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Have you ever thought about what a Neural Network tries to do? 🤔 Why does it work? 🤔 Let's try to understand visually 👁️🔎 (🚨 no heavy math) 1/7🧵

6

29

158

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

My Christmas gift arrived and right on time for my eoy break! 🤩 Thanks @fchollet for the great work and sharing your knowledge with the community! The book looks great!

Tweet media one

8

4

156

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

💡Machine Learning🤖🧠 models are designed to make predictions and not giving you insights. If you have a bunch of data and want to find out "interesting" things about it, use Statistical approaches! [20 seconds]👀 1/4🧵

5

28

155

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Machine Learning🤖🧠 models can be classified regarding how much human supervision they need. 🧐 This affects the algorithms used and the types of tasks that it can solve. You can categorize Machine Learning models in 4 major categories: 👇🏽

2

24

147

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

🤖🧠🧮 To start with Machine Learning you don't need to understand the Math part in all the details But if you want to have a better grasp of why and how the "magic" works, here are the topics you'll need to learn: 👇

4

31

148

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Why do we need the yield keyword in Python🐍? To understand it, you need to know what is a: • Generator • Iterables • Lazy evaluation Quick thread to start the week... [2 minutes] 1/10🧵

4

21

144

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Today I'm completing 22 years as a professional developer!🎈🥳🎉🎊🎂 👴🏽 Ask me anything!

30

3

143

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Reached 17000 followers! 🤯🤯🤯 To the moon… 🌔 🚀 . . . . . . . . . . 💥 🌏 Thanks everyone

15

3

140

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Let's start with some theory I've been working with ML on the Audio domain and at first I couldn't understand much but as I kept reading I managed to figure out some things. Let me share some of the basic theory with you: [10 minutes read] 1/n🧵

6

28

140

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Machine learning goes beyond Neural Networks Sometimes a simpler technique might give you way better results and much easier to understand A very versatile family of algorithms are Decision Forests 🌴🌲🌳? Let me tell you how they work… 1/10🧵

5

28

136

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

4 years

Today I learned that you can unpack assignments using a starred expression! 🤯 It's called catch-all unpacking () This is better than using slicing and indexing in some situations because it's easier to read and maintain.

Tweet media one

7

14

132

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

⛔️: for i in range(len(my_collection)) ✅: for i, item in enumerate(my_collection)) #python

8

12

132

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

@simonw Pandas, even for millions of rows

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Imagine you need to load a very large (eg: 5.7GB) csv file to train your model!🤔 This is a very common problem in real world situations and also in many Kaggle competitions! How can we use Pandas 🐼 effectively to do that? Let's dive in… [2 effective min] 1/10🧵

28

266

1K

2

3

132

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

This is one reason why people are afraid of contributing to the community -Divam did a great job! spent their time creating something super cool and shared with everyone -Just to have someone come and shi* on their head for no reason! This is very sad! Don't be like that!

Tweet media one

17

10

131

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

@nilmoretto Meu chute sem ser biologo mas sendo cientista da computacao é: -> Leptoglossus occidentalis tambem conhecido como western conifer seed bug 👈🏾🌱🪲 Meu metodo pra descobri: - baixa a image (ou da um screenshot) - usa esta na pagina aqui:

Google | aiy | Kaggle

Food classification model.

2

3

119

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

How is your weekend going? 🤸🤸🤸 Not bad for an old fat dude!😉 Any tips @Simone_Biles ?

16

1

126

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

📱+🤖🧠 Pixel 7 phones were announced this week and if you like Machine Learning, specifically on-device ML, this release brings a lot of cool features! These are my top 5 best ML features: 👇

Tweet media one

12

20

127

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

When you use environments like Google Colab, Jupyter Notebooks or Kaggle Kernels, you have access to Magic Commands🪄 Let me explain how they work��️, why they matter🤔 and how to create one yourself🏗️ [1 min] 1/12🧵

4

20

123

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

What is JAX? JAX is Autograd and XLA, brought together for high-performance numerical computing and ML research. It provides composable transformations of Python+NumPy programs: differentiate, vectorize, parallelize, JIT compile to GPU/TPU, and more. 🤔🧐 #30DaysOfJAX 1/11🧵

1

24

125

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

4 years

Why do you need a train, validation and a test dataset? The train is obvious, it's what your model learns from. To avoid overfitting (memorizing) or underfitting you need to try your model with unseen data and that's why you need validation/test datasets. But why both? 1/4🧵

7

21

121

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Today is my daughter's birthday! 🎂🎉🎉🎉 She wants to be a scientist so we created her future lego set for when she's very famous! Leave a like for her! I'll print it later as a gift!

Tweet media one

8

4

120

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

When I was studying for my technical interviews I used a couple of different resources Here is a list of the 4 most important ones.. [And some bonus ones! 🎁🎁] [1 minute of investment] 1/8🧵

3

30

120

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

One concept that helped me learn Machine Learning is: -> Transfer Learning 🧐🧠➡️🤓 Let's make an analogy: learning a new programming language. [30 sec] 1/5🧵

1

11

118

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Today I'm presenting TensorFlow on an MiT workshop! 🤯🤯🤯 I don't even know if I have proper clothing to do that!

10

3

120

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

@svpino Since I skipped the ones for learning the language, my main reference is Effective Python. It's a great book if you already know Python and want to write better code.

Tweet media one

2

9

118

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

I failed my first Google interview process 😭 Sometimes we fail and that's fine!👍🏽 I've failed many times and in crucial life changing moments 😱 The tip I can give you is: ✅Learn from your failures and grow with them💪🏽 ⬆️Use what you've learned and do better next time!

4

8

118

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

@msoares Cara quite legal! Excelente trabalho! Em 2013 eu e o @jay_santos criamos um site pra analisar gastos de deputados e também tivemos diversos problemas mas vimos vários gastos estranhos com combustível e tudo que vc imaginar Infelizmente por falta de tempo matamos o projeto...

2

3

113

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

@GergelyOrosz “… 40 hours per week or depart Tesla. This is less than we ask of factory workers” Looks like a great place to work...

0

4

116

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Imagine you want to pair two sequences into only one: a = [💤,🦠,🧮] b = [🥱,🤒,🤓] c = [[🥱,💤],[🦠,🤒],[🧮,🤓]] Python🐍 has the Zip function to do just that! c = zip(a,b) But what if you want to go from c back to a and b?

6

13

115

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Are you afraid of the code interviews?😱😱😱 You're not alone!🫂 I've done many on both sides (candidate and interviewer)! Here are some tips that helped me succeed: 👍🏾👍🏾👍🏾 [1.5 minutes] 1/10🧵

4

16

116

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

TIL! Did you know about this? ( @__mharrison__ , @driscollis , @python_engineer , @mathsppblog )

@KhuyenTran16

Khuyen Tran

2 years

Have you ever wanted to add a math description for your #Python function but found it time-consuming to do so? latexify_py allows you to add LaTex math description with only one decorator. Link to latexify_py:

Tweet media one

79

1K

7K

3

15

114

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

It's balloons-on-my-profile-page day!!! 🎈🎈🎈🥳🎉🎊🪅 The only 🎁 I want is to be able to keep sharing good Machine Learning 🤖🧠 and Python🐍 content that helps you grow everyday!

34

3

112

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

I learned many of these tricks on this great Kaggle Kernel: Go give a +1 to it as it really deserves! 9/10🧵

Tweet card media

How to import a CSV file of 55 million rows

Explore and run machine learning code with Kaggle Notebooks | Using data from New York City Taxi Fare Prediction

2

11

106

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

9 months

Finally I can talk about what I've been working for a while!!! welcome Gemini!!

@GoogleDeepMind

Google DeepMind

@GoogleDeepMind

9 months

We’re excited to announce 𝗚𝗲𝗺𝗶𝗻𝗶: @Google ’s largest and most capable AI model. Built to be natively multimodal, it can understand and operate across text, code, audio, image and video - and achieves state-of-the-art performance across many tasks. 🧵

171

2K

6K

8

14

102

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

To train a ML model, you need a train, validation and a test dataset The train split is clear, it's what your model learns from To avoid overfitting or underfitting you need to try your model with unseen data and that's why you need validation/test datasets But why both?🤔 🧵

Tweet media one

4

14

99

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Say 👋 to Luna She's going to help with Machine Learning, Python and Cuteness content creation

Tweet media one

Tweet media two

11

3

98

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Machine Learning on-device is looking like magic!🤯 🤖+🧠+📱 = 🪄🪄✨✨🧙🏾‍♂️🧙🏾 Before -> (seconds) After #magiceraser

Tweet media one

Tweet media two

6

8

98

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Hoje conheci ao vivo uma das pessoas mais incríveis aqui do Twitter: @import_robs Aprendi tanto sobre física e astronomia que estou quase achando Interestelar fácil de entender! 🤯 Obrigado pelo papo Roberta! Sua paixão pelo seu trabalho é inspiradora! 🤖🧠+🌌

Tweet media one

5

2

96

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

OMG!!!😱 I'm 10 followers away from 5K! Do you think you can help me get there? Please share this with your friends that are interested in Machine Learning, Python and tech career tips!

Tweet media one

7

9

98

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Do you wanna learn a cool Python🐍 feature today? ➡️ list slice notation🔪 Python's regular array indexing as in multiple languages is: a[index] a = [0, 1, 2, 3, 4] a[0] == 0 👇

4

15

96

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

This week so far: - Presented 7+ hours of TensorFlow content to universities and big companies 🤖🧠🥑🗣️ - Joined an internal hackathon, with two projects 👨🏾‍💻 (14 teams participated) - Got first and second place in the internal hackathon! 🥇🥈 🥳🎉🎊 Not bad, not bad at all!

8

3

95

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

1 year

@mekkaokerekebye Another weird fact is that, allegedly, this lady escaped a cult in the past but couldn't foresee a new one!

6

10

92

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

day 8 of #30daysofml on Kaggle! After a good basic Python week, today we start with Machine Learning! The two topics that are mentioned are Decision Trees 🌳🌲🎄🌴 and Pandas 🐼 1/4🧵

4

17

91

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

Which Machine Learning content creators would you recommend?

20

15

94

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Today, after 6 years of deciding to leave my country, family and friends to chase a better life, I can say that I achieved adulthood: I own a mortgage! I'm very happy!

Tweet media one

20

0

92

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

2 years

This is insane! As of now, the model is taking less than 4 seconds per image!!!! (batch_size = 8) 🤯🤯🤯 and without changing anything on the model!

Tweet media one

@fchollet

François Chollet

2 years

Here's a TPU inference example on Colab: The Colab TPU is actually slower than GPU for single-image generation, but you do get a speedup when generating a large batch (8+ images).

4

10

81

6

6

93

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

In two hours (11:59AM BST) I'll open my DM Feel free to ask questions about: • Python 🐍 • Machine Learning 🤖🧠 • TensorFlow 🦾 • DevRel 🥑🗣️ Talk to you soon!!

4

10

89

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Python has one very good built-in module to deal with collections called itertools Its functions form an "iterator algebra" that is fast and memory efficient. They are inspired by the ones in APL, SML and Haskel Let's take a look on some of them: count, cycle and repeat 1/5🧵

3

7

93

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Working with smarter people than you is sometimes very hard for your ego! There's a lot of impostor syndrome in the beginning. But that's a big chance to learn what these smarter people do that you can adapt and grow as bigger fish 🦈. 3/11🧵

1

4

91

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Closing a great month with this! Thanks @TensorFlow 🏆🤩🥳🎊🎉

Tweet media one

Tweet media two

4

2

91

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

"()()" is not palindrome ")(()" is palindrome What? 🤔🤔🤔🤔 [25 sec] 1/5🧵

4

16

91

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Given you have your data loaded on a Pandas 🐼Dataframe. How can you understand more about its characteristics?🤔🧐 Let's see a couple of options...👇🏾👇🏾👇🏾 [30 quick sec] 1/5🧵

5

15

90

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

Today I decided to study music generation 🎹🎵🎶 🇮🇪using Machine Learning 🧠🤖. I followed the great MiT course more specifically the third class exercise (lab 1) and I got some nice tunes! Check it out! what do you think @lmoroney ? 1/5🧵

5

10

91

@gusthema

Gus (🤖🧠+🐍+🥑🗣️)

3 years

@atchimolajuwon @William_Castro o que piora ainda mais é ele ter a audiencia que tem e normalizando isso do: "eu acho a, b, c pq é minha percepcao sem embasamento nenhum pq é chato." olha que exemplão legal.... por isso eu marquei o canal dele pra nunca ser uma recomendacao pra mim no youtube!

1

1

87