Latest deals
Technology
Apple
Artificial Intelligence
Big Data
Cyber Security
Gadgets
Startup
Cloud Computing
More
Drone
Mobile
Robotics
Software Development
Search
Home
Tags
Translation
Tag: translation
Technology
The departure of a top White House tech advisor sparks concern about data security and continuity.
admin
-
December 3, 2024
0
Mobile
The original text: Google Translate gets a brand new Sticky Translation mode that remembers your final used mode. Improved text: Google Translate now features a Sticky Translation mode that retains the last mode you used.
admin
-
November 27, 2024
0
Gadgets
Introducing Solos’ latest innovation: the Xeon 6 and 7 smartglasses, featuring cutting-edge technology that combines ChatGPT 4.0 with real-time language translation in 25 languages. Building on this momentum, Solos is poised to revolutionize the industry again with its upcoming AirGo V smartglasses, which boast AI-powered object recognition capabilities, further bridging the gap between humans and machines.
admin
-
November 14, 2024
0
Artificial Intelligence
What’s driving interest in neural machine translation is the ability to learn consideration from vast amounts of bilingual data. This post explores the creation of a simple neural machine translation system utilizing the Keras deep learning library and TensorFlow as the backend. “`python import numpy as np from keras.layers import Embedding, Dense, LSTM from keras.models import Model class NeuralMachineTranslator: def __init__(self, source_vocabulary_size, target_vocabulary_size): self.source_embedding = Embedding(input_dim=source_vocabulary_size, output_dim=128, mask_zero=True) self.target_embedding = Embedding(input_dim=target_vocabulary_size, output_dim=128, mask_zero=True) encoder_input = self.source_embedding.input encoder_hidden_state = LSTM(256)(self.source_embedding(encoder_input)) decoder_input = Dense(256)(encoder_hidden_state) decoder_output = LSTM(256, return_sequences=True)(decoder_input) self.model = Model(inputs=self.source_embedding.input, outputs=decoder_output) def translate(self, source_sentence): encoder_input = np.zeros((1, len(source_sentence), 128)) for i in range(len(source_sentence)): word_vector = self.source_embedding.get_weights()[0][source_sentence[i]] encoder_input[0, i] = word_vector output = self.model.predict(encoder_input) return [np.argmax(output[0, i]) for i in range(len(source_sentence))] translator = NeuralMachineTranslator(10000, 5000) print(translator.translate([‘hello’, ‘world’])) “`
admin
-
November 4, 2024
0
Artificial Intelligence
What’s driving innovation in computer vision today? It’s the ability to transform one image into another based on a given picture.
admin
-
October 30, 2024
0
Startup
EasyTranslate thinks augmenting LLMs with people will give it an edge over pure AI translation companies
admin
-
June 26, 2024
0
1
2
Page 2 of 2
![What’s driving interest in neural machine translation is the ability to learn consideration from vast amounts of bilingual data. This post explores the creation of a simple neural machine translation system utilizing the Keras deep learning library and TensorFlow as the backend. “`python import numpy as np from keras.layers import Embedding, Dense, LSTM from keras.models import Model class NeuralMachineTranslator: def __init__(self, source_vocabulary_size, target_vocabulary_size): self.source_embedding = Embedding(input_dim=source_vocabulary_size, output_dim=128, mask_zero=True) self.target_embedding = Embedding(input_dim=target_vocabulary_size, output_dim=128, mask_zero=True) encoder_input = self.source_embedding.input encoder_hidden_state = LSTM(256)(self.source_embedding(encoder_input)) decoder_input = Dense(256)(encoder_hidden_state) decoder_output = LSTM(256, return_sequences=True)(decoder_input) self.model = Model(inputs=self.source_embedding.input, outputs=decoder_output) def translate(self, source_sentence): encoder_input = np.zeros((1, len(source_sentence), 128)) for i in range(len(source_sentence)): word_vector = self.source_embedding.get_weights()[0][source_sentence[i]] encoder_input[0, i] = word_vector output = self.model.predict(encoder_input) return [np.argmax(output[0, i]) for i in range(len(source_sentence))] translator = NeuralMachineTranslator(10000, 5000) print(translator.translate([‘hello’, ‘world’])) “`](https://i2.wp.com/blogs.rstudio.com/tensorflow/posts/2018-07-30-attention-layer/images/attention.png?w=768&resize=768,0&ssl=1 "What’s driving interest in neural machine translation is the ability to learn consideration from vast amounts of bilingual data. This post explores the creation of a simple neural machine translation system utilizing the Keras deep learning library and TensorFlow as the backend. “`python import numpy as np from keras.layers import Embedding, Dense, LSTM from keras.models import Model class NeuralMachineTranslator: def __init__(self, source_vocabulary_size, target_vocabulary_size): self.source_embedding = Embedding(input_dim=source_vocabulary_size, output_dim=128, mask_zero=True) self.target_embedding = Embedding(input_dim=target_vocabulary_size, output_dim=128, mask_zero=True) encoder_input = self.source_embedding.input encoder_hidden_state = LSTM(256)(self.source_embedding(encoder_input)) decoder_input = Dense(256)(encoder_hidden_state) decoder_output = LSTM(256, return_sequences=True)(decoder_input) self.model = Model(inputs=self.source_embedding.input, outputs=decoder_output) def translate(self, source_sentence): encoder_input = np.zeros((1, len(source_sentence), 128)) for i in range(len(source_sentence)): word_vector = self.source_embedding.get_weights()[0][source_sentence[i]] encoder_input[0, i] = word_vector output = self.model.predict(encoder_input) return [np.argmax(output[0, i]) for i in range(len(source_sentence))] translator = NeuralMachineTranslator(10000, 5000) print(translator.translate([‘hello’, ‘world’])) “`")
